├── .gitignore ├── README.md ├── code ├── domains.py ├── news_classifications.py ├── process_bakshy.py ├── process_grinberg.py ├── process_robertson.py └── process_yin.py ├── data ├── bias_scores │ ├── README.md │ └── bias_scores.csv ├── domain_coding │ ├── bakshy2015.csv │ ├── data │ │ ├── Domain Codings.xlsx │ │ ├── black_sites.txt │ │ └── website_alignment_scores.xlsx │ ├── grinberg2019.tsv │ ├── joseph2019.csv │ ├── news.tsv │ ├── robertson2018.csv │ └── yin2018.csv ├── domains.tsv └── fake_news.tsv └── replicate.sh /.gitignore: -------------------------------------------------------------------------------- 1 | /venv -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # domains 2 | 3 | A repository for aggregating __web domain metrics__, like partisanship or veracity classification, from peer reviewed publications. All data gathering and aggregating can be replicated by running `bash replicate.sh`. If you're looking for the final product see: `data/domains.tsv` 4 | 5 | 6 | News is classifications are available in the `news_is_news` column, and are defined using: 7 | 1. 488 domains identified as ‘hard news’ by Bakshy et al. (2015) 8 | 2. 1,250 domains manually identified as news by Grinberg et al. (2019), and 9 | 3. 6,288 domains aggregated from local news listings by Yin (2018) 10 | 11 | 12 | Currently includes data from: 13 | 14 | Grinberg, N., Joseph, K., Friedland, L., Swire-Thompson, B., & Lazer, D. (2019). Fake news on Twitter during the 2016 US presidential election. Science, 363(6425), 374-378. [Download data](https://github.com/LazerLab/twitter-fake-news-replication/tree/master/domains/domain_coding/data) 15 | 16 | Robertson, R. E., Jiang, S., Joseph, K., Friedland, L., Lazer, D., & Wilson, C. (2018). Auditing Partisan Audience Bias within Google Search. Proceedings of the ACM on Human-Computer Interaction, 2(CSCW), 148. [Download data](http://personalization.ccs.neu.edu/static/archive/bias_scores.tar.gz) 17 | 18 | Leon Yin. (2018). yinleon/LocalNewsDataset: Initial release (V1.0). Zenodo. https://doi.org/10.5281/zenodo.1345145 19 | 20 | Robertson et al. (2018) includes data from: 21 | - AllSides. 2018. Media Bias Ratings. AllSides. (2018). [Download Data](https://www.allsides.com/media-bias/media-bias-ratings) 22 | - Amy Mitchell, Jeffrey Gottfried, Jocelyn Kiley, and Katerina Eva Matsa. 2014. Political Polarization & Media Habits. Pew Research Center’s Journalism Project. (Oct. 2014). [Download data](https://assets.pewresearch.org/wp-content/uploads/sites/13/2014/10/Political-Polarization-and-Media-Habits-FINAL-REPORT-7-27-15.pdf) 23 | - Ceren Budak, Sharad Goel, and Justin M Rao. 2016. Fair and balanced? Quantifying media bias through crowdsourced content analysis. Public Opinion Quarterly 80, S1 (2016), 250–271. [Download data](https://deepblue.lib.umich.edu/data/concern/data_sets/8w32r569d?locale=en) 24 | - Eytan Bakshy, Solomon Messing, and Lada A Adamic. 2015. Exposure to ideologically diverse news and opinion on Facebook. Science 348, 6239 (2015), 1130–1132. [Download data](https://science.sciencemag.org/content/sci/suppl/2015/05/06/science.aaa1160.DC1/Bakshy-SM.revision.1.pdf) 25 | 26 | 27 | 28 | 29 | -------------------------------------------------------------------------------- /code/domains.py: -------------------------------------------------------------------------------- 1 | """ Aggregate external data keyed by domain 2 | """ 3 | 4 | import os 5 | import pandas as pd 6 | 7 | # In 8 | DATA_DIR = os.path.join('data', 'domain_coding') 9 | FP_NEWS = os.path.join(DATA_DIR, 'news.tsv') 10 | FP_BIAS = os.path.join(DATA_DIR, 'robertson2018.csv') 11 | FP_FAKE_NEWS = os.path.join(DATA_DIR, 'grinberg2019.tsv') 12 | 13 | # Out 14 | FP_DOMAINS = os.path.join(DATA_DIR, 'domains.tsv') 15 | 16 | # Load data 17 | bias = pd.read_csv(FP_BIAS) 18 | news = pd.read_csv(FP_NEWS, sep='\t') 19 | fakenews = pd.read_csv(FP_FAKE_NEWS, sep='\t') 20 | 21 | # Unique domains 22 | domain_set = set() 23 | for df in [bias, news, fakenews]: 24 | domain_set |= set(df.domain) 25 | 26 | # Merge all domain data 27 | domains = news.merge(bias, how='outer', on='domain') 28 | domains = domains.merge(fakenews, how='outer', on='domain') 29 | 30 | # # Combine unreliable news columns - no NewsGuard in public release 31 | # domains['fake_either'] = ( 32 | # (domains['fn_is_fake'] == 1) | 33 | # (domains['newsguard_is_fake'] == 1) 34 | # ).astype(float) 35 | 36 | # Save ------------------------------------------------------------------------- 37 | 38 | domains.to_csv(FP_DOMAINS, sep='\t', index=False) 39 | print(f'saved: {FP_DOMAINS} - {domains.shape[0]:,}') 40 | -------------------------------------------------------------------------------- /code/news_classifications.py: -------------------------------------------------------------------------------- 1 | """ News classifications 2 | 3 | The following values are smaller than those listed in the paper because 4 | it only considers unique domains, and some domains were repeated in each 5 | dataset. 6 | 7 | joseph2019.csv was provided by Kenny Joseph, and contains news classifications from Grinberg et al. (2019). 8 | 9 | """ 10 | 11 | import os 12 | import numpy as np 13 | import pandas as pd 14 | 15 | def get_news_class(row): 16 | if row.isnull().all(): 17 | return None 18 | elif (row == True).any(): 19 | return True 20 | else: 21 | return False 22 | 23 | DATA_DIR = os.path.join('data', 'domains') 24 | FP_JOSEPH = os.path.join(DATA_DIR, 'joseph2019.csv') 25 | FP_BAKSHY = os.path.join(DATA_DIR, 'bakshy2015.csv') 26 | FP_YIN = os.path.join(DATA_DIR, 'yin2018.csv') 27 | FP_NEWS_OUT = os.path.join(DATA_DIR, 'news.tsv') 28 | 29 | # Load data -------------------------------------------------------------------- 30 | 31 | joseph2019 = pd.read_csv(FP_JOSEPH) 32 | newsguard = pd.read_csv(FP_NEWSGUARD) 33 | bakshy2015 = pd.read_csv(FP_BAKSHY) 34 | yin2018 = pd.read_csv(FP_YIN) 35 | 36 | # Reshape and merge ------------------------------------------------------------ 37 | 38 | # Use joseph2019 aggregated datasets as base news 39 | news = joseph2019.copy() 40 | 41 | # Add Bakshy classifications 42 | keep_cols = ['domain', 'bakshy_is_news'] 43 | news = news.merge(bakshy2015[keep_cols], how='outer', on='domain') 44 | news.rename(columns={'bakshy_is_news':'bakshy'}, inplace=True) 45 | 46 | # Add Yin classifications 47 | keep_cols = ['domain', 'yin_is_news'] 48 | news = news.merge(yin2018[keep_cols], how='outer', on='domain') 49 | news.rename(columns={'yin_is_news':'yin'}, inplace=True) 50 | 51 | # Format 52 | news.set_index('domain', inplace=True) 53 | news = news.astype(float) 54 | 55 | # Overall news classification based on a subset of data sources 56 | use_cols = ['fakenews_proj', 'yin', 'bakshy'] 57 | news['n'] = news[use_cols].sum(axis=1) 58 | news['is_news'] = (news.n > 0).astype(float) 59 | 60 | prefix_cols = [f'news_{c}' for c in news] 61 | news.columns = prefix_cols 62 | 63 | # Save 64 | news.to_csv(FP_NEWS_OUT, sep='\t') 65 | print(f"saved: {FP_NEWS_OUT} - {news.shape[0]:,}") 66 | -------------------------------------------------------------------------------- /code/process_bakshy.py: -------------------------------------------------------------------------------- 1 | """ News Classifications from Bakshy et al. 2015 2 | 3 | https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/AAI7VA 4 | 5 | """ 6 | 7 | import os 8 | import re 9 | import utils # see https:/github.com/gitronald/utils 10 | import pandas as pd 11 | 12 | # Filepaths 13 | DIR_DATA = os.path.join('data', 'domains') 14 | FP_IN = os.path.join(DIR_DATA, 'bakshy2015_top500.txt') 15 | FP_OUT = os.path.join('data', 'domains', 'bakshy2015.csv') 16 | 17 | # Load data 18 | bakshy = pd.read_csv(FP_IN) 19 | 20 | # Standardize domains 21 | bakshy['domain'] = bakshy['domain'].apply(utils.web.get_domain) 22 | 23 | # Drop duplicates by taking mean score (Bakshy has 5 cases of www + non-www) 24 | # E.g. www.washingtonexaminer.com, 0.8124 and washingtonexaminer.com, 0.8285 25 | cols = [c for c in bakshy if c != 'domain'] 26 | bakshy = bakshy.groupby("domain")[cols].mean() 27 | 28 | # As in Guess 2021, we exclude platforms in this dataset, and also remove satire 29 | bakshy['is_news'] = 1 30 | exclude_domains = [ 31 | 'en.wikipedia.org', # wikipedia explicitly says they're not news 32 | 'youtube.com', 'm.youtube.com', # platforms 33 | 'amazon.com', 'twitter.com', 'vimeo.com', 34 | 'theonion.com', # satire 35 | ] 36 | mask = bakshy.index.isin(exclude_domains) 37 | bakshy.loc[mask, 'is_news'] = 0 38 | 39 | # Add column prefix 40 | bakshy = bakshy.add_prefix('bakshy_') 41 | 42 | # Save 43 | bakshy.to_csv(FP_OUT) 44 | print(f'saved: {FP_OUT} - {bakshy.shape[0]:,}') 45 | -------------------------------------------------------------------------------- /code/process_grinberg.py: -------------------------------------------------------------------------------- 1 | """ Fake news classifications 2 | 3 | Color-coded fake news domain classifications from this paper: 4 | Grinberg et al. 2019. Fake news on Twitter during the 2016 U.S. presidential 5 | election. Science, Vol. 363, Issue 6425, pp. 374-378. DOI: 10.1126/science.aau2706 6 | 7 | Classification data obtained from replication materials here: 8 | https://doi.org/10.5281/zenodo.2483311 9 | 10 | """ 11 | 12 | import os 13 | import re 14 | import utils 15 | import pandas as pd 16 | 17 | # In data 18 | DIR_DATA = os.path.join('data', 'domain_coding', 'data') 19 | FP_BLACK_LIST = os.path.join(DIR_DATA, 'black_sites.txt') 20 | FP_FAKE_NEWS_IN = os.path.join(DIR_DATA, 'Domain Codings.xlsx') 21 | 22 | # Out data 23 | FP_FAKE_NEWS_OUT = os.path.join('data', 'domain_coding', 'grinberg2019.tsv') 24 | 25 | # Load data 26 | blacklist = pd.read_csv(FP_BLACK_LIST, header=None) 27 | blacklist[1] = 'black' 28 | blacklist.columns = ['domain', 'color'] 29 | 30 | fakenews = pd.read_excel(FP_FAKE_NEWS_IN, engine='openpyxl') 31 | fakenews.columns = ['_'.join(re.split(r'\s+', c.lower())) for c in fakenews] 32 | fakenews.rename(columns={'likelihood_rating':'color'}, inplace=True) 33 | fakenews['color'] = fakenews['color'].str.lower() 34 | fakenews = fakenews[['domain', 'color']] 35 | 36 | # Append black listed domains 37 | fakenews = fakenews.append(blacklist, sort=False) 38 | fakenews.dropna(subset=['domain'], inplace=True) 39 | 40 | # Clean domain names 41 | fakenews['domain'] = fakenews.domain.str.lower().str.strip() 42 | 43 | # Standardize domains 44 | fakenews['domain'] = fakenews['domain'].apply(utils.web.get_domain) 45 | 46 | # Add an aggregate col 47 | fakenews['is_fake'] = fakenews.color.isin(['black','red','orange']) 48 | fakenews['is_fake'] = fakenews.is_fake.astype(float) 49 | 50 | prefix_cols = [f'fn_{c}' if c != 'domain' else c for c in fakenews] 51 | fakenews.columns = prefix_cols 52 | 53 | # Print summary 54 | # tab = pd.crosstab(fakenews.fn_color, fakenews.fn_is_fake, margins=True)\ 55 | # .T[:2][['black','red','orange','yellow','green','satire']] 56 | # print(tab) 57 | 58 | # Save 59 | fakenews.to_csv(FP_FAKE_NEWS_OUT, index=False, sep='\t') 60 | print(f"saved: {FP_FAKE_NEWS_OUT} - {fakenews.shape[0]:,}") 61 | -------------------------------------------------------------------------------- /code/process_robertson.py: -------------------------------------------------------------------------------- 1 | """Process Robertson 2018 data 2 | 3 | Data from my previous project. Contains an aggregation of partisan bias scores from four sources, as well as scores developed in the paper. 4 | 5 | """ 6 | 7 | import os 8 | import utils # see https:/github.com/gitronald/utils 9 | import pandas as pd 10 | 11 | DATA_DIR = os.path.join('data') 12 | FP_BIAS_IN = os.path.join(DATA_DIR, 'bias_scores', 'bias_scores.csv') 13 | FP_BIAS_OUT = os.path.join(DATA_DIR, 'robertson2018.csv') 14 | 15 | # Load 16 | bias = pd.read_csv(FP_BIAS_IN) 17 | 18 | # Add prefix to partisan bias score column names 19 | bias.set_index('domain', inplace=True) 20 | bias = bias.add_prefix('bias_') 21 | 22 | # Fix domains with URL params: 23 | # 1. vyper.io?utm_source= 24 | # 2. home.twibble.io?utm_source=twitter&utm_medium=social&utm_campaign=poweredby 25 | # 26 | # Looking into N shares, these urls were shared by 500 and 1400 unique 27 | # accounts, repectively, and neither domain exists in the dataset without 28 | # the parameters. Together this suggests that the score applies to the 29 | # domain, and not the domain + these specific parameters. 30 | bias = bias.reset_index() 31 | bias['domain'] = bias['domain'].apply(utils.web.get_domain) 32 | 33 | # Drop duplicates after standardizing (removes domain:433 sites), keep 34 | # record/score with more unique accounts sharing it 35 | bias = (bias.sort_values(['domain', 'bias_rounded_n_accts']) 36 | .drop_duplicates(subset=['domain'], keep='last')) 37 | 38 | # Drop 39 | bias.set_index('domain', inplace=True) 40 | 41 | # Save 42 | bias.to_csv(FP_BIAS_OUT) 43 | print(f'saved: {FP_BIAS_OUT} - {bias.shape[0]:,}') -------------------------------------------------------------------------------- /code/process_yin.py: -------------------------------------------------------------------------------- 1 | """ News Classifications from Yin (2018) LocalNewsDataset 2 | 3 | Source: https://github.com/yinleon/LocalNewsDataset 4 | 5 | """ 6 | 7 | import os 8 | import utils # see https:/github.com/gitronald/utils 9 | import pandas as pd 10 | 11 | # Filepaths 12 | DIR_DATA = os.path.join('data', 'domain_coding') 13 | FP_IN = os.path.join(DIR_DATA,'local_news_dataset_2018_for_domain_analysis.csv') 14 | FP_OUT = os.path.join('data', 'domain_coding', 'yin2018.csv') 15 | 16 | # Load data 17 | yin = pd.read_csv(FP_IN) 18 | 19 | # Standardize domains and set all as news 20 | yin['domain'] = yin['domain'].apply(utils.web.get_domain) 21 | yin['is_news'] = 1 22 | 23 | # Drop string column 24 | mask = yin.domain == 'alaska broadcast television' 25 | yin = yin[~mask] 26 | 27 | # Exclude MySpace as a domain from this dataset 28 | exclude_domains = ['myspace.com'] 29 | mask = yin.domain.isin(exclude_domains) 30 | yin.loc[mask, 'is_news'] = 0 31 | 32 | # Add column prefix 33 | yin.set_index("domain", inplace=True) 34 | yin = yin.add_prefix('yin_') 35 | 36 | # Save 37 | yin.to_csv(FP_OUT) 38 | print(f'saved: {FP_OUT} - {yin.shape[0]:,}') 39 | -------------------------------------------------------------------------------- /data/bias_scores/README.md: -------------------------------------------------------------------------------- 1 | # Partisan Audience Bias Scores 2 | 3 | These scores were derived from the sharing patterns of web domains by ~500K known Democrats and Republicans on Twitter. The scores scale from -1 (shared only by Democrats) to 1 (shared only by Republicans), and we excluded domains shared by less than 50 unique accounts. More details on the scores are available in our paper, which you can download [here](http://ronalderobertson.com/robertson2018auditing.pdf). 4 | 5 | We provide our scores below for research purposes only. To prevent the potential for reidentification, all scores have been rounded to four digits past the decimal and we provide the number of tweets and unique accounts that shared a domain rounded to the nearest 100. We also provide the partisan bias scores from several other projects that we used to validate our scores. 6 | 7 | If you use our scores, please cite our work: 8 | 9 | Robertson, R. E., Jiang, S., Joseph, K., Friedland, L., Lazer, D., & Wilson, C. (2018). Auditing partisan audience bias within Google Search. In Proceedings of the ACM: Human-Computer Interaction, 1(2), Article 148. DOI: 10.1145/3274417. 10 | 11 | BibTeX citation: 12 | ``` 13 | @article{robertson2018auditing, 14 | title={Auditing Partisan Audience Bias within Google Search}, 15 | author={Robertson, Ronald E and Jiang, Shan and Joseph, Kenneth and Friedland, Lisa and Lazer, David and Wilson, Christo}, 16 | journal={Proceedings of the ACM on Human-Computer Interaction}, 17 | volume={2}, 18 | number={CSCW}, 19 | pages={148}, 20 | year={2018}, 21 | publisher={ACM} 22 | } 23 | ``` 24 | -------------------------------------------------------------------------------- /data/domain_coding/bakshy2015.csv: -------------------------------------------------------------------------------- 1 | domain,bakshy_avg_align,bakshy_l2,bakshy_l1,bakshy_n,bakshy_r1,bakshy_r2,bakshy_is_news 2 | 100percentfedup.com,0.856,0.0,0.0,0.0006,0.4212,0.5783,1 3 | 10tv.com,-0.0984,0.0203,0.2057,0.693,0.0744,0.0065,1 4 | 11alive.com,0.0686,0.0088,0.1699,0.5958,0.2211,0.0043,1 5 | 6abc.com,-0.5037,0.0925,0.406,0.4659,0.0349,0.0007,1 6 | 7online.com,-0.4067,0.0751,0.2747,0.6391,0.0093,0.0018,1 7 | 800whistleblower.com,0.8268,0.0002,0.0003,0.0038,0.5081,0.4876,1 8 | 9news.com,-0.032,0.0332,0.1355,0.6571,0.16,0.0143,1 9 | aattp.org,-0.8936,0.9486,0.0509,0.0004,0.0001,0.0,1 10 | abc11.com,-0.19,0.074,0.3381,0.4908,0.0926,0.0045,1 11 | abc13.com,0.0097,0.0283,0.1498,0.6534,0.1644,0.0041,1 12 | abc7.com,-0.31,0.1301,0.3264,0.4026,0.1345,0.0065,1 13 | abc7chicago.com,-0.503,0.1239,0.4502,0.3851,0.0389,0.0019,1 14 | abcnews.go.com,-0.1605,0.0505,0.2642,0.5222,0.1082,0.0548,1 15 | aclj.org,0.9268,0.0,0.0,0.0001,0.0645,0.9354,1 16 | aclu.org,-0.7686,0.7872,0.1607,0.0485,0.0018,0.0018,1 17 | act.weareultraviolet.org,-0.971,0.152,0.848,0.0,0.0,0.0,1 18 | addictinginfo.org,-0.8894,0.9392,0.0607,0.0001,0.0,0.0,1 19 | advocate.com,-0.9276,0.9609,0.035,0.0025,0.0005,0.001,1 20 | againstcronycapitalism.org,0.6857,0.0,0.0002,0.0196,0.9008,0.0795,1 21 | al.com,0.009,0.0999,0.1739,0.2678,0.4035,0.0549,1 22 | alan.com,-0.9009,0.9275,0.0657,0.0064,0.0004,0.0,1 23 | algemeiner.com,0.4456,0.0,0.0084,0.4891,0.4591,0.0433,1 24 | aljazeera.com,-0.5895,0.3394,0.5653,0.0828,0.0116,0.0009,1 25 | allenbwest.com,0.8918,0.0,0.0,0.0,0.4003,0.5997,1 26 | allenwestrepublic.com,0.9423,0.0,0.0,0.0,0.0255,0.9745,1 27 | alternativemediasyndicate.com,-0.5579,0.0859,0.8821,0.032,0.0,0.0,1 28 | alternet.org,-0.8804,0.8854,0.1049,0.0082,0.0014,0.0001,1 29 | amazon.com,0.0362,0.1249,0.1045,0.3318,0.2043,0.2345,0 30 | america.aljazeera.com,-0.7362,0.6974,0.2804,0.02,0.0018,0.0004,1 31 | americannews.com,0.8651,0.0,0.0,0.0,0.4532,0.5468,1 32 | americanoverlook.com,0.8311,0.0,0.0,0.0015,0.6537,0.3448,1 33 | americanthinker.com,0.9112,0.0003,0.0,0.0021,0.2326,0.765,1 34 | americasfreedomfighters.com,0.8523,0.0,0.0,0.0006,0.6225,0.3769,1 35 | anonhq.com,-0.4102,0.0005,0.8179,0.1816,0.0,0.0,1 36 | aol.com,0.0133,0.1762,0.2883,0.3116,0.1765,0.0474,1 37 | app.actionsprout.com,-0.6993,0.5989,0.3427,0.0102,0.0338,0.0144,1 38 | armytimes.com,0.4171,0.0001,0.0039,0.1808,0.8134,0.0018,1 39 | atlantablackstar.com,-0.7055,0.4158,0.5792,0.0047,0.0,0.0003,1 40 | attn.com,-0.7747,0.4775,0.522,0.0,0.0005,0.0,1 41 | azcentral.com,-0.1731,0.2588,0.2675,0.2794,0.1725,0.0218,1 42 | azfamily.com,0.0439,0.0201,0.1375,0.5371,0.2922,0.0131,1 43 | baltimoresun.com,-0.1321,0.0959,0.3362,0.2029,0.3162,0.0488,1 44 | bangordailynews.com,-0.1732,0.1389,0.1918,0.3944,0.236,0.039,1 45 | barackobama.com,-0.8077,0.988,0.0114,0.0,0.0006,0.0,1 46 | barenakedislam.com,0.8589,0.0,0.0,0.0106,0.4226,0.5667,1 47 | barracudabrigade.net,0.9381,0.0,0.0,0.0021,0.2317,0.7662,1 48 | battleforthenet.com,-0.5612,0.0,1.0,0.0,0.0,0.0,1 49 | baynews9.com,0.0586,0.033,0.1161,0.4403,0.3937,0.0169,1 50 | bbc.co.uk,-0.3313,0.0784,0.5507,0.336,0.0284,0.0065,1 51 | bbc.com,-0.2609,0.1099,0.474,0.3527,0.0551,0.0083,1 52 | bearingarms.com,0.77,0.0,0.0,0.0,0.9525,0.0475,1 53 | beforeitsnews.com,0.5876,0.0052,0.0638,0.1368,0.6653,0.1289,1 54 | benswann.com,0.4846,0.001,0.0287,0.2702,0.6719,0.0283,1 55 | bigstory.ap.org,-0.2022,0.3084,0.2015,0.224,0.1324,0.1337,1 56 | billmoyers.com,-0.839,0.9448,0.0549,0.0004,0.0,0.0,1 57 | bizpacreview.com,0.9142,0.0,0.0,0.0001,0.1646,0.8352,1 58 | blackamericaweb.com,-0.7772,0.9077,0.0796,0.0122,0.0005,0.0,1 59 | blogs.wsj.com,-0.0746,0.1248,0.195,0.2316,0.404,0.0445,1 60 | bloomberg.com,-0.1565,0.1124,0.2377,0.3086,0.223,0.1183,1 61 | bluenationreview.com,-0.8883,0.9771,0.0226,0.0003,0.0,0.0,1 62 | boingboing.net,-0.7779,0.6098,0.356,0.0319,0.0012,0.0011,1 63 | bostonglobe.com,-0.4446,0.3414,0.3056,0.2657,0.0756,0.0118,1 64 | brainfall.com,-0.0483,0.0005,0.0005,0.56,0.439,0.0,1 65 | breakingisraelnews.com,0.7086,0.0,0.0012,0.0101,0.8687,0.12,1 66 | breitbart.com,0.9136,0.0001,0.0003,0.0052,0.2169,0.7775,1 67 | briefly.today,-0.3198,0.0921,0.0142,0.8471,0.0,0.0465,1 68 | businessinsider.com,-0.0585,0.0562,0.2693,0.4515,0.144,0.0789,1 69 | businessweek.com,-0.2615,0.16,0.3551,0.3364,0.1224,0.0261,1 70 | buzzfeed.com,-0.5242,0.2537,0.4295,0.2777,0.0337,0.0054,1 71 | buzzpo.com,0.976,0.0,0.0003,0.0,0.0217,0.9779,1 72 | c-span.org,-0.0442,0.1102,0.3374,0.2087,0.2203,0.1234,1 73 | caintv.com,0.934,0.0,0.0,0.0,0.0237,0.9762,1 74 | capitalisminstitute.org,0.9044,0.0,0.0,0.0,0.0234,0.9766,1 75 | catholicnewsagency.com,0.5209,0.0003,0.0293,0.2101,0.7088,0.0515,1 76 | cbsnews.com,-0.127,0.1373,0.2552,0.4506,0.1309,0.0259,1 77 | change.org,-0.3442,0.2275,0.2548,0.243,0.2301,0.0447,1 78 | charismanews.com,0.871,0.0003,0.0,0.0019,0.3694,0.6283,1 79 | chicago.cbslocal.com,-0.2568,0.1648,0.1308,0.1721,0.5205,0.0117,1 80 | chicagotribune.com,-0.3117,0.2086,0.3793,0.2949,0.0893,0.0279,1 81 | christiannews.net,0.807,0.0,0.0,0.0002,0.7419,0.2579,1 82 | christianpost.com,0.6722,0.0039,0.067,0.0468,0.4626,0.4198,1 83 | clashdaily.com,0.9218,0.0,0.0,0.0022,0.2291,0.7687,1 84 | cleveland.com,-0.4428,0.1802,0.4955,0.2325,0.0826,0.0093,1 85 | click2houston.com,0.1329,0.0263,0.1694,0.4954,0.2393,0.0696,1 86 | clickondetroit.com,-0.3654,0.0685,0.3284,0.5902,0.0088,0.0041,1 87 | cnbc.com,0.0503,0.0662,0.1803,0.5125,0.1776,0.0635,1 88 | cnn.com,-0.2705,0.0372,0.5139,0.3944,0.0452,0.0093,1 89 | cnsnews.com,0.89865,0.0001,0.0001,0.00125,0.121,0.8775,1 90 | collective-evolution.com,-0.3014,0.0004,0.2856,0.7061,0.0076,0.0003,1 91 | commondreams.org,-0.9673,0.8944,0.0945,0.0108,0.0001,0.0002,1 92 | conservativebyte.com,0.9063,0.0,0.0,0.0012,0.1732,0.8256,1 93 | conservativeinfidel.com,0.9306,0.0,0.0002,0.0002,0.1713,0.8283,1 94 | conservativeoutfitters.com,0.8686,0.0,0.0,0.0,0.3583,0.6417,1 95 | conservativepost.com,0.8962,0.0,0.0,0.0001,0.1449,0.855,1 96 | conservativerefocus.com,0.9457,0.0,0.0,0.0035,0.5746,0.4219,1 97 | conservativetribune.com,0.8866,0.0,0.0,0.0001,0.1305,0.8693,1 98 | controversialtimes.com,0.7836,0.0,0.0002,0.0327,0.807,0.1601,1 99 | countercurrentnews.com,-0.556,0.071,0.8636,0.0625,0.003,0.0,1 100 | courant.com,-0.1968,0.0346,0.0986,0.7826,0.0689,0.0153,1 101 | crooksandliars.com,-0.9218,0.9145,0.0799,0.0024,0.003,0.0002,1 102 | cruz.senate.gov,0.8733,0.0005,0.0,0.0006,0.027,0.9719,1 103 | d.shpg.org,-0.8971,0.8823,0.1161,0.0011,0.0005,0.0,1 104 | dailycaller.com,0.8697,0.0006,0.0058,0.0087,0.1828,0.8021,1 105 | dailycurrant.com,-0.375,0.1463,0.4309,0.1162,0.3066,0.0,1 106 | dailydot.com,-0.5961,0.2917,0.6939,0.0138,0.0004,0.0002,1 107 | dailykos.com,-0.8972,0.9674,0.0291,0.0008,0.0026,0.0,1 108 | dailymail.co.uk,0.286,0.0747,0.1254,0.2482,0.4025,0.1491,1 109 | dailysignal.com,0.9319,0.0,0.0,0.0006,0.0347,0.9647,1 110 | dailysurge.com,0.9195,0.0,0.0,0.0032,0.3281,0.6688,1 111 | dcbeacon.com,0.8735,0.0,0.0,0.0012,0.264,0.7348,1 112 | dcclothesline.com,0.806,0.0004,0.0003,0.1259,0.4729,0.4006,1 113 | dcgazette.com,0.883,0.0,0.0,0.0001,0.6104,0.3896,1 114 | defund.com,0.8898,0.0,0.0001,0.0186,0.3135,0.6678,1 115 | democracynow.org,-0.934,0.9555,0.0401,0.0039,0.0,0.0004,1 116 | denverpost.com,-0.2012,0.228,0.3503,0.2763,0.1082,0.0372,1 117 | dineshdsouza.com,0.937,0.0,0.0,0.0,0.0132,0.9868,1 118 | downtrend.com,0.9136,0.0,0.0,0.0001,0.6681,0.3318,1 119 | duffelblog.com,0.5205,0.0004,0.0003,0.0662,0.9263,0.0068,1 120 | eaglerising.com,0.9018,0.0,0.0,0.0001,0.1366,0.8633,1 121 | earthweareone.com,-0.4698,0.0317,0.946,0.0188,0.0035,0.0,1 122 | economist.com,-0.3173,0.0623,0.5229,0.3545,0.0585,0.0018,1 123 | ecowatch.com,-0.8554,0.727,0.2505,0.0079,0.0147,0.0,1 124 | edition.cnn.com,-0.2615,0.0475,0.4382,0.4606,0.05,0.0037,1 125 | egbertowillies.com,-0.8701,0.9199,0.0801,0.0,0.0,0.0,1 126 | electronicintifada.net,-0.8074,0.6126,0.3827,0.0043,0.0005,0.0,1 127 | elitedaily.com,-0.2558,0.0086,0.1559,0.7929,0.0411,0.0016,1 128 | empirenews.net,-0.0158,0.0651,0.0697,0.2359,0.6291,0.0001,1 129 | en.what-character-are-you.com,-0.009,0.0,0.0102,0.9898,0.0,0.0,1 130 | en.wikipedia.org,-0.2145,0.1241,0.3189,0.3352,0.1607,0.0611,0 131 | endtime.com,0.8043,0.0,0.0,0.0036,0.6801,0.3163,1 132 | endtimeheadlines.org,0.7572,0.0,0.0004,0.0117,0.7654,0.2225,1 133 | examiner.com,0.3807,0.0909,0.0415,0.2467,0.2679,0.353,1 134 | farrahgray.com,-0.7616,0.633,0.3613,0.0045,0.0008,0.0003,1 135 | filmingcops.com,-0.389,0.0015,0.8157,0.1821,0.0006,0.0001,1 136 | finance.yahoo.com,0.0777,0.0192,0.2044,0.452,0.291,0.0333,1 137 | firstcoastnews.com,0.1755,0.0038,0.1102,0.4629,0.4129,0.0101,1 138 | firstlook.org,-0.6805,0.4541,0.4526,0.0916,0.0018,0.0,1 139 | fivethirtyeight.com,-0.5225,0.7152,0.218,0.061,0.0052,0.0007,1 140 | forbes.com,0.0563,0.2931,0.1552,0.2036,0.2153,0.1327,1 141 | foreignpolicy.com,-0.1516,0.054,0.3584,0.5113,0.0533,0.023,1 142 | forwardprogressives.com,-0.8744,0.9836,0.0124,0.0039,0.0001,0.0,1 143 | fox10phoenix.com,0.2386,0.009,0.1008,0.5047,0.369,0.0165,1 144 | fox13now.com,0.0538,0.0139,0.1027,0.6975,0.1551,0.0308,1 145 | fox2now.com,-0.1395,0.0127,0.2088,0.652,0.126,0.0004,1 146 | fox4kc.com,0.0444,0.0089,0.1016,0.795,0.0925,0.002,1 147 | fox59.com,0.0195,0.0108,0.1185,0.6819,0.1829,0.0059,1 148 | fox6now.com,-0.0939,0.0254,0.216,0.6701,0.0815,0.0071,1 149 | fox8.com,-0.1676,0.0172,0.2584,0.6883,0.0338,0.0024,1 150 | foxbaltimore.com,-0.1907,0.0342,0.4627,0.3849,0.0775,0.0408,1 151 | foxcarolina.com,0.3233,0.0119,0.028,0.3652,0.5698,0.0252,1 152 | foxnews.com,0.7754,0.0011,0.0026,0.0089,0.5328,0.4547,1 153 | foxnewsinsider.com,0.8334,0.0001,0.0003,0.0003,0.5829,0.4164,1 154 | freebeacon.com,0.8778,0.0002,0.0005,0.0015,0.1789,0.819,1 155 | freedomoutpost.com,0.9042,0.0001,0.0,0.0019,0.2134,0.7846,1 156 | freep.com,-0.4596,0.2845,0.4516,0.1895,0.0458,0.0286,1 157 | frontpagemag.com,0.9284,0.0005,0.0,0.0031,0.3435,0.6529,1 158 | funker530.com,0.5984,0.0,0.0,0.0022,0.9969,0.0009,1 159 | gawker.com,-0.7749,0.7067,0.251,0.0395,0.002,0.0008,1 160 | gizmodo.com,-0.3002,0.0206,0.6327,0.324,0.0219,0.0008,1 161 | glennbeck.com,0.969,0.0,0.0,0.0,0.008,0.992,1 162 | globalgrind.com,-0.8729,0.9076,0.0917,0.0007,0.0,0.0,1 163 | globalresearch.ca,-0.252,0.0563,0.3456,0.3787,0.2139,0.0054,1 164 | gma.yahoo.com,-0.0472,0.0146,0.1902,0.6248,0.1653,0.0051,1 165 | gop.com,0.9268,0.0,0.0,0.0006,0.0224,0.977,1 166 | gopthedailydose.com,0.9386,0.0001,0.0,0.0002,0.1501,0.8496,1 167 | gothamist.com,-0.7415,0.6293,0.1973,0.1701,0.0033,0.0,1 168 | grist.org,-0.8452,0.8697,0.1254,0.0049,0.0,0.0,1 169 | guns.com,0.7536,0.0278,0.0081,0.0164,0.651,0.2966,1 170 | gunssavelives.net,0.7862,0.0,0.0,0.0013,0.8212,0.1775,1 171 | haaretz.com,-0.504,0.3243,0.4004,0.187,0.0839,0.0045,1 172 | hannity.com,0.9444,0.0,0.0,0.0007,0.0113,0.988,1 173 | headlinepolitics.com,0.8898,0.0,0.0,0.0001,0.1043,0.8955,1 174 | healthimpactnews.com,0.5548,0.0,0.0006,0.0831,0.912,0.0043,1 175 | hemp.org,-0.5268,0.0888,0.8613,0.0483,0.0015,0.0,1 176 | hightimes.com,-0.47665,0.0074,0.9613,0.03115,0.00015,0.0,1 177 | hlntv.com,-0.2211,0.0061,0.2287,0.7574,0.0069,0.001,1 178 | host.madison.com,-0.7585,0.8052,0.1324,0.0306,0.0126,0.0191,1 179 | hosted.ap.org,0.5827,0.0202,0.0151,0.0785,0.2666,0.6195,1 180 | hotair.com,0.9247,0.0,0.0,0.0031,0.1276,0.8694,1 181 | huffingtonpost.ca,-0.469,0.2037,0.1846,0.5069,0.1024,0.0024,1 182 | huffingtonpost.co.uk,-0.4205,0.3074,0.2002,0.4776,0.0133,0.0015,1 183 | huffingtonpost.com,-0.6176,0.3618,0.3306,0.2914,0.0149,0.0013,1 184 | humanevents.com,0.9303,0.0,0.0,0.0005,0.2326,0.767,1 185 | huzlers.com,-0.4188,0.001,0.1645,0.8336,0.0,0.0009,1 186 | ibtimes.co.uk,0.0264,0.0672,0.3565,0.1594,0.3504,0.0665,1 187 | ibtimes.com,-0.1405,0.1825,0.351,0.2039,0.2177,0.0448,1 188 | iflscience.com,-0.4537,0.0299,0.9209,0.0491,0.0,0.0001,1 189 | ifyouonlynews.com,-0.8964,0.9322,0.0642,0.0036,0.0,0.0,1 190 | ijreview.com,0.8901,0.0,0.0,0.0002,0.2207,0.7792,1 191 | independent.co.uk,-0.3598,0.1904,0.4933,0.2079,0.0781,0.0304,1 192 | indiancountrytodaymedianetwork.com,-0.692,0.3031,0.6836,0.013,0.0,0.0003,1 193 | infowars.com,0.5997,0.0004,0.0076,0.1195,0.8103,0.0622,1 194 | inquisitr.com,0.0977,0.083,0.1943,0.1818,0.5026,0.0384,1 195 | insider.foxnews.com,0.8239,0.0,0.0,0.0035,0.4779,0.5186,1 196 | investigations.peta.org,-0.4281,0.0,1.0,0.0,0.0,0.0,1 197 | io9.com,-0.6232,0.2943,0.6491,0.0554,0.0005,0.0008,1 198 | israelnationalnews.com,0.7646,0.0006,0.0084,0.0841,0.6565,0.2504,1 199 | israelvideonetwork.com,0.706,0.0,0.0002,0.1059,0.8363,0.0576,1 200 | jewishpress.com,0.5559,0.0014,0.0077,0.1672,0.6922,0.1315,1 201 | jewsnews.co.il,0.6922,0.0001,0.0003,0.0066,0.8715,0.1215,1 202 | jezebel.com,-0.9487,0.9498,0.0473,0.0026,0.0,0.0003,1 203 | jihadwatch.org,0.839,0.0,0.0003,0.008,0.5119,0.4798,1 204 | joeforamerica.com,0.8878,0.0,0.0,0.0001,0.3923,0.6076,1 205 | jpost.com,0.4149,0.0036,0.0311,0.2302,0.6856,0.0495,1 206 | jrn.com,-0.0377,0.0369,0.141,0.5534,0.2397,0.0291,1 207 | jsonline.com,-0.4045,0.5193,0.168,0.1575,0.0622,0.0929,1 208 | judicialwatch.org,0.8287,0.0,0.0,0.0005,0.5471,0.4524,1 209 | kansascity.com,-0.4023,0.3862,0.3835,0.1385,0.064,0.0279,1 210 | kctv5.com,-0.2071,0.0252,0.1974,0.6986,0.0709,0.0079,1 211 | kdvr.com,0.0225,0.0411,0.1847,0.6127,0.1492,0.0124,1 212 | kfor.com,0.1097,0.046,0.046,0.494,0.408,0.0061,1 213 | kgw.com,-0.2359,0.0366,0.4823,0.4621,0.0156,0.0033,1 214 | khou.com,0.1182,0.0173,0.0795,0.594,0.2956,0.0135,1 215 | kirotv.com,-0.1907,0.0225,0.2303,0.6444,0.0969,0.0058,1 216 | kmov.com,-0.1538,0.0599,0.2601,0.5578,0.1144,0.0079,1 217 | koco.com,0.1027,0.0216,0.0814,0.3404,0.5495,0.007,1 218 | komonews.com,-0.1643,0.0394,0.2861,0.5702,0.096,0.0083,1 219 | kptv.com,-0.0685,0.0064,0.1604,0.8088,0.0237,0.0007,1 220 | ksdk.com,-0.1001,0.0413,0.1456,0.7159,0.0904,0.0068,1 221 | ktla.com,-0.2287,0.17,0.3056,0.3242,0.1931,0.0072,1 222 | kxan.com,-0.039,0.0608,0.1202,0.6763,0.1316,0.0112,1 223 | latimes.com,-0.3995,0.2597,0.4813,0.1613,0.0772,0.0205,1 224 | latino.foxnews.com,0.2312,0.0164,0.0558,0.1035,0.7015,0.1228,1 225 | leftaction.com,-0.8878,0.9979,0.0021,0.0,0.0,0.0,1 226 | legalinsurrection.com,0.8557,0.0,0.0,0.0171,0.0935,0.8894,1 227 | lgbtqnation.com,-0.8501,0.9272,0.0724,0.0004,0.0,0.0,1 228 | liberalamerica.org,-0.9387,0.9855,0.0145,0.0,0.0,0.0,1 229 | libertynews.com,0.8947,0.0,0.0,0.0059,0.2888,0.7053,1 230 | lifenews.com,0.9664,0.0,0.0,0.0096,0.0989,0.8915,1 231 | lifesitenews.com,0.9366,0.0,0.0003,0.0002,0.1266,0.8728,1 232 | liveactionnews.org,0.9228,0.0,0.0,0.0,0.5694,0.4306,1 233 | liveleak.com,0.3231,0.0289,0.0853,0.2843,0.4209,0.1806,1 234 | local10.com,-0.3545,0.0344,0.2441,0.6994,0.0205,0.0016,1 235 | lovebscott.com,-0.883,0.9941,0.0059,0.0,0.0,0.0,1 236 | m.cnsnews.com,0.8665,0.0,0.0009,0.01,0.3132,0.6759,1 237 | m.nydailynews.com,-0.2295,0.1907,0.2693,0.3784,0.1542,0.0074,1 238 | m.youtube.com,0.105,0.1045,0.3193,0.1477,0.2203,0.2082,0 239 | madamenoire.com,-0.8568,0.9732,0.0268,0.0,0.0,0.0,1 240 | madworldnews.com,0.8609,0.0,0.0019,0.0268,0.4473,0.524,1 241 | marinecorpstimes.com,0.5372,0.0003,0.0005,0.0689,0.9252,0.0052,1 242 | mashable.com,-0.4106,0.1874,0.387,0.3678,0.0546,0.0032,1 243 | mediaite.com,-0.1326,0.174,0.2657,0.1785,0.2062,0.1757,1 244 | mediamatters.org,-0.8509,0.913,0.0675,0.0038,0.011,0.0047,1 245 | miamiherald.com,-0.3418,0.3308,0.4055,0.1951,0.0507,0.018,1 246 | mic.com,-0.7083,0.731,0.2392,0.0262,0.0034,0.0002,1 247 | middleeastmonitor.com,-0.6544,0.2207,0.7376,0.0363,0.004,0.0013,1 248 | military.com,0.4081,0.0091,0.0033,0.2139,0.7588,0.0148,1 249 | militarytimes.com,0.4459,0.0002,0.001,0.2094,0.7838,0.0055,1 250 | mlive.com,-0.3186,0.1699,0.3374,0.3744,0.1007,0.0176,1 251 | mondoweiss.net,-0.7135,0.4727,0.5067,0.0184,0.0019,0.0003,1 252 | money.cnn.com,-0.2565,0.0416,0.4745,0.4516,0.0298,0.0024,1 253 | motherjones.com,-0.8663,0.9397,0.052,0.008,0.0002,0.0,1 254 | mrctv.org,0.8636,0.0,0.0001,0.0003,0.2275,0.7722,1 255 | msn.com,-0.084,0.0184,0.2891,0.5583,0.1244,0.0098,1 256 | msnbc.com,-0.8102,0.894,0.0762,0.0089,0.0178,0.003,1 257 | myfox8.com,-0.021,0.0073,0.1739,0.5759,0.2397,0.0032,1 258 | myfoxal.com,0.0788,0.022,0.1066,0.3927,0.4735,0.0052,1 259 | myfoxchicago.com,-0.342,0.0185,0.5575,0.4087,0.0131,0.0021,1 260 | myfoxdetroit.com,-0.3483,0.058,0.6436,0.2821,0.0144,0.0018,1 261 | myfoxdfw.com,0.1633,0.057,0.0983,0.4965,0.3298,0.0183,1 262 | myfoxny.com,-0.0713,0.0157,0.3312,0.5468,0.0783,0.028,1 263 | myfoxtampabay.com,0.1475,0.0262,0.0718,0.6636,0.229,0.0095,1 264 | myfoxtwincities.com,-0.1171,0.0331,0.2195,0.6817,0.0624,0.0034,1 265 | nahadaily.com,-0.7746,0.9659,0.0341,0.0,0.0,0.0,1 266 | nation.foxnews.com,0.9012,0.0004,0.0,0.0103,0.3154,0.6739,1 267 | nationaljournal.com,0.0191,0.1802,0.1557,0.2037,0.2025,0.2579,1 268 | nationalprolifealliance.com,0.9108,0.0,0.0,0.0,0.0902,0.9098,1 269 | nationalreport.net,0.1168,0.2179,0.0656,0.4874,0.1648,0.0642,1 270 | nationalreview.com,0.9009,0.0005,0.0033,0.0033,0.1678,0.825,1 271 | nationalrighttolifenews.org,0.9739,0.0,0.0,0.0,0.0158,0.9842,1 272 | nationofchange.org,-0.8262,0.6131,0.3814,0.0055,0.0,0.0,1 273 | naturalnews.com,0.4837,0.0007,0.0004,0.3101,0.6812,0.0077,1 274 | navytimes.com,0.3365,0.0,0.0017,0.3005,0.6945,0.0032,1 275 | nbcbayarea.com,-0.5023,0.2271,0.5329,0.2262,0.0124,0.0013,1 276 | nbcchicago.com,-0.3416,0.1363,0.3201,0.4343,0.0999,0.0094,1 277 | nbcconnecticut.com,-0.1992,0.0145,0.2984,0.6606,0.0198,0.0067,1 278 | nbcdfw.com,0.1204,0.0383,0.0292,0.646,0.2559,0.0305,1 279 | nbclosangeles.com,-0.2456,0.0674,0.448,0.4248,0.0515,0.0082,1 280 | nbcnews.com,-0.2735,0.0494,0.4467,0.4368,0.0641,0.003,1 281 | nbcnewyork.com,-0.3704,0.0655,0.5105,0.3652,0.0565,0.0023,1 282 | nbcphiladelphia.com,-0.3285,0.0737,0.5449,0.3026,0.0769,0.0019,1 283 | nbcsandiego.com,-0.1038,0.0211,0.2682,0.6178,0.0858,0.0072,1 284 | nbcwashington.com,-0.4291,0.0977,0.4602,0.278,0.1619,0.0021,1 285 | newjersey.news12.com,-0.2447,0.0542,0.294,0.6268,0.0231,0.0018,1 286 | newnownext.com,-0.9097,0.0648,0.9352,0.0,0.0,0.0,1 287 | newrepublic.com,-0.6695,0.7501,0.1501,0.0946,0.0041,0.0011,1 288 | news.investors.com,0.8955,0.0,0.0015,0.0097,0.2219,0.7668,1 289 | news.kron4.com,-0.6604,0.3254,0.6199,0.0534,0.0006,0.0007,1 290 | news.msn.com,-0.0623,0.0129,0.2379,0.6027,0.144,0.0025,1 291 | news.vice.com,-0.4284,0.1333,0.6371,0.2143,0.0139,0.0014,1 292 | news.yahoo.com,0.0493,0.026,0.2373,0.4892,0.2168,0.0308,1 293 | news9.com,0.1417,0.0133,0.1824,0.441,0.3475,0.0159,1 294 | newsbusters.org,0.9168,0.0001,0.0,0.0003,0.0306,0.969,1 295 | newsiosity.com,0.6111,0.0,0.0026,0.0574,0.6172,0.3229,1 296 | newsmax.com,0.7697,0.0062,0.01,0.0708,0.5034,0.4096,1 297 | newsninja2012.com,0.8971,0.0,0.0006,0.0396,0.5611,0.3988,1 298 | newsone.com,-0.7794,0.7554,0.2393,0.0049,0.0003,0.0001,1 299 | newsweek.com,-0.2726,0.2297,0.5144,0.1681,0.0778,0.01,1 300 | newyork.cbslocal.com,-0.2017,0.0483,0.2296,0.5132,0.1975,0.0114,1 301 | newyorker.com,-0.7584,0.8642,0.1235,0.0078,0.0043,0.0002,1 302 | next-genpatriots.com,0.8144,0.0003,0.0,0.0047,0.3244,0.6706,1 303 | nj.com,-0.2969,0.1198,0.3462,0.4338,0.0884,0.0119,1 304 | nola.com,-0.2175,0.1882,0.3151,0.2893,0.1415,0.066,1 305 | nowtheendbegins.com,0.8533,0.0,0.0046,0.0002,0.4914,0.5038,1 306 | npr.org,-0.6103,0.4501,0.4682,0.0732,0.0081,0.0003,1 307 | nraila.org,0.8529,0.0018,0.0,0.0014,0.6561,0.3406,1 308 | nrcc.org,0.9257,0.0,0.0,0.0,0.0104,0.9896,1 309 | numbersusa.com,0.8549,0.0,0.0,0.0008,0.7799,0.2193,1 310 | nydailynews.com,-0.2139,0.1461,0.3943,0.2983,0.1445,0.0168,1 311 | nypost.com,0.2497,0.0115,0.1175,0.2374,0.5029,0.1306,1 312 | nytimes.com,-0.5469,0.4281,0.3689,0.1255,0.0749,0.0027,1 313 | occupydemocrats.com,-0.899,0.9928,0.0072,0.0,0.0,0.0,1 314 | odmp.org,0.5967,0.0003,0.0012,0.0084,0.9779,0.0122,1 315 | okcfox.com,0.1296,0.0248,0.1147,0.4955,0.3442,0.0209,1 316 | online.wsj.com,0.2764,0.0171,0.1282,0.2796,0.3487,0.2263,1 317 | opposingviews.com,0.2685,0.0115,0.0104,0.216,0.7617,0.0004,1 318 | ora.tv,-0.2014,0.0004,0.7156,0.2391,0.0434,0.0015,1 319 | oregonlive.com,-0.3203,0.1426,0.485,0.1323,0.1775,0.0627,1 320 | pamelageller.com,0.8632,0.0,0.0,0.0003,0.3702,0.6294,1 321 | patch.com,-0.0102,0.0325,0.1333,0.6676,0.1421,0.0245,1 322 | patheos.com,-0.2624,0.4381,0.2407,0.1222,0.0532,0.1459,1 323 | patriotnewswire.com,0.829,0.0,0.0,0.0,0.4544,0.5456,1 324 | patriotupdate.com,0.8892,0.0012,0.0,0.0005,0.2774,0.7209,1 325 | pbs.org,-0.5393,0.1467,0.7293,0.0753,0.0464,0.0022,1 326 | people.com,-0.2034,0.017,0.247,0.7051,0.0296,0.0013,1 327 | personalliberty.com,0.8637,0.0,0.0002,0.0161,0.6313,0.3524,1 328 | petitions.whitehouse.gov,-0.2005,0.2485,0.3023,0.1295,0.103,0.2168,1 329 | philly.com,-0.3668,0.2933,0.3064,0.3035,0.0746,0.0221,1 330 | pittsburgh.cbslocal.com,-0.1747,0.1059,0.1431,0.6705,0.0564,0.0241,1 331 | pix11.com,-0.5719,0.1315,0.5237,0.1324,0.212,0.0004,1 332 | pjmedia.com,0.9125,0.0,0.0003,0.0018,0.1627,0.8353,1 333 | policeone.com,0.5063,0.0002,0.0003,0.0382,0.9591,0.0022,1 334 | policestateusa.com,-0.0106,0.1203,0.028,0.7885,0.062,0.0011,1 335 | politicalears.com,0.8225,0.0,0.0001,0.0006,0.5361,0.4632,1 336 | politico.com,-0.1334,0.1215,0.2799,0.2149,0.2573,0.1264,1 337 | politicususa.com,-0.9037,0.994,0.0055,0.0001,0.0005,0.0,1 338 | politifact.com,-0.4802,0.4754,0.431,0.0514,0.0208,0.0213,1 339 | popularmilitary.com,0.4461,0.0,0.0033,0.1239,0.8612,0.0116,1 340 | prepperchimp.com,0.8496,0.0,0.0,0.0006,0.4394,0.56,1 341 | presstv.ir,-0.4142,0.1495,0.5204,0.2566,0.0588,0.0147,1 342 | q13fox.com,-0.0132,0.0114,0.1315,0.7234,0.1253,0.0083,1 343 | qpolitical.com,0.861,0.0,0.0,0.0027,0.3813,0.616,1 344 | quiznatic.com,0.2979,0.0656,0.0111,0.1108,0.7307,0.0818,1 345 | quizony.com,-0.0018,0.2098,0.1305,0.053,0.0876,0.5191,1 346 | qz.com,-0.4713,0.3859,0.4177,0.1855,0.0062,0.0047,1 347 | radio.foxnews.com,0.6973,0.0044,0.0147,0.0129,0.3649,0.6031,1 348 | rare.us,0.6386,0.0003,0.0013,0.029,0.8119,0.1574,1 349 | rawstory.com,-0.8534,0.8366,0.1598,0.0022,0.0011,0.0003,1 350 | readersupportednews.org,-0.9984,0.8215,0.1755,0.0028,0.0002,0.0,1 351 | reagancoalition.com,0.8878,0.0,0.0,0.0004,0.3484,0.6512,1 352 | realclearpolitics.com,0.6616,0.0161,0.065,0.0574,0.3529,0.5086,1 353 | reason.com,0.3502,0.0091,0.0378,0.2825,0.5811,0.0895,1 354 | redflagnews.com,0.9163,0.0001,0.0002,0.0058,0.3044,0.6896,1 355 | redstate.com,0.9624,0.0002,0.0,0.0007,0.0685,0.9306,1 356 | reuters.com,-0.0945,0.0973,0.2818,0.3729,0.1829,0.0652,1 357 | reverbpress.com,-0.8922,0.9404,0.0596,0.0,0.0,0.0,1 358 | rightwingnews.com,0.88795,0.0,0.0,0.0,0.3033,0.6967000000000001,1 359 | rightwingwatch.org,-0.9407,0.8874,0.1046,0.006,0.002,0.0,1 360 | ringoffireradio.com,-0.9472,0.9861,0.0134,0.0005,0.0,0.0,1 361 | rollingstone.com,-0.6487,0.5395,0.4189,0.0364,0.0052,0.0001,1 362 | rt.com,-0.1488,0.0157,0.3891,0.5164,0.075,0.0037,1 363 | rushlimbaugh.com,1.0077,0.0,0.0,0.0,0.0021,0.9979,1 364 | sacramento.cbslocal.com,-0.1622,0.0574,0.3573,0.4637,0.0942,0.0274,1 365 | salon.com,-0.8753,0.8951,0.0987,0.0042,0.002,0.0001,1 366 | samuel-warde.com,-0.9095,0.9372,0.0628,0.0,0.0,0.0,1 367 | sanders.senate.gov,-0.8528,0.8903,0.1097,0.0,0.0,0.0,1 368 | scgnews.com,0.1063,0.0021,0.104,0.8363,0.0576,0.0,1 369 | secretsofthefed.com,0.0666,0.01,0.0374,0.7975,0.0789,0.0763,1 370 | secure.nrdconline.org,-0.6553,0.3558,0.5217,0.086,0.0366,0.0,1 371 | secure3.convio.net,-0.6422,0.2187,0.3215,0.3904,0.068,0.0014,1 372 | sfgate.com,-0.581,0.4248,0.4295,0.0788,0.0545,0.0125,1 373 | share.credoaction.com,-0.8941,0.9637,0.0349,0.0014,0.0,0.0001,1 374 | shoebat.com,0.8703,0.0,0.0003,0.0018,0.4355,0.5624,1 375 | silive.com,-0.0627,0.0581,0.1643,0.5826,0.1877,0.0073,1 376 | slate.com,-0.6813,0.6183,0.3083,0.0606,0.0112,0.0016,1 377 | sonsoflibertymedia.com,0.9286,0.0,0.0,0.0002,0.1663,0.8336,1 378 | stltoday.com,-0.309,0.1738,0.338,0.3954,0.0806,0.0122,1 379 | stripes.com,0.3658,0.0027,0.0116,0.2253,0.7375,0.023,1 380 | student-debt-forgiveness.com,-0.5858,0.054,0.8958,0.0496,0.0,0.0006,1 381 | tacticalshit.com,0.8118,0.0004,0.0,0.0031,0.6813,0.3152,1 382 | takepart.com,-0.7045,0.6588,0.3134,0.0267,0.001,0.0,1 383 | talkingpointsmemo.com,-0.8614,0.8155,0.1473,0.0109,0.0258,0.0005,1 384 | tampabay.com,-0.4745,0.5919,0.2405,0.1056,0.0421,0.0199,1 385 | teaparty.org,0.9423,0.0001,0.0001,0.0011,0.188,0.8108,1 386 | teapartycrusaders.com,0.8525,0.0007,0.0005,0.0161,0.3096,0.6731,1 387 | ted.com,-0.4859,0.049,0.8185,0.1234,0.0074,0.0017,1 388 | telegraph.co.uk,0.0269,0.0449,0.2161,0.3433,0.323,0.0728,1 389 | tellmenow.com,0.7818,0.0001,0.0001,0.1245,0.7366,0.1387,1 390 | theantimedia.org,-0.3584,0.0032,0.8089,0.1861,0.0017,0.0,1 391 | theatlantic.com,-0.5424,0.3608,0.5057,0.1155,0.0163,0.0018,1 392 | theblaze.com,0.8887,0.0,0.0004,0.0043,0.3091,0.6862,1 393 | thecolbertreport.cc.com,-0.6937,0.6752,0.2911,0.0325,0.0012,0.0,1 394 | thedailybeast.com,-0.4561,0.2756,0.4463,0.1215,0.1393,0.0173,1 395 | thedailyshow.cc.com,-0.6704,0.6918,0.2423,0.0452,0.0203,0.0005,1 396 | thedenverchannel.com,-0.012,0.0429,0.1817,0.5704,0.1911,0.0139,1 397 | theeverlastinggopstoppers.com,-0.8928,0.9458,0.0542,0.0,0.0,0.0,1 398 | thefederalist.com,0.8559,0.0,0.1095,0.0157,0.1852,0.6897,1 399 | thefederalistpapers.org,0.8659,0.0,0.0067,0.0002,0.3221,0.671,1 400 | thefreethoughtproject.com,-0.3618,0.0191,0.7108,0.2692,0.0008,0.0001,1 401 | thegatewaypundit.com,0.9389,0.0,0.0031,0.0074,0.297,0.6925,1 402 | thegrio.com,-0.8326,0.9113,0.0886,0.0001,0.0,0.0,1 403 | theguardian.com,-0.5723,0.485,0.3601,0.123,0.0294,0.0025,1 404 | thehill.com,0.1661,0.1358,0.1426,0.1613,0.3789,0.1813,1 405 | themindunleashed.org,-0.4008,0.0025,0.8098,0.1877,0.0,0.0,1 406 | theminorityreportblog.com,0.9026,0.0,0.0004,0.0001,0.1707,0.8288,1 407 | thenation.com,-0.9463,0.8956,0.1011,0.003,0.0001,0.0002,1 408 | thenewamerican.com,0.7993,0.0005,0.0027,0.0146,0.6039,0.3783,1 409 | thenewcivilrightsmovement.com,-0.9643,0.9869,0.0072,0.0059,0.0,0.0,1 410 | theonion.com,-0.5516,0.1887,0.7312,0.0794,0.0005,0.0001,0 411 | thepcmdgazette.com,0.8222,0.1585,0.0017,0.0117,0.4742,0.3539,1 412 | thepetitionsite.com,-0.6,0.4272,0.4916,0.0688,0.0094,0.003,1 413 | thepolicewifelifeblog.com,0.6271,0.0,0.0,0.0,1.0,0.0,1 414 | thepoliticalinsider.com,0.8998,0.0,0.0,0.0001,0.0989,0.901,1 415 | therightscoop.com,0.9275,0.0,0.0007,0.0011,0.2792,0.719,1 416 | theroot.com,-0.7792,0.8379,0.1552,0.0067,0.0001,0.0002,1 417 | thetruthaboutguns.com,0.6965,0.0,0.0046,0.0227,0.8515,0.1212,1 418 | theuspatriot.com,0.8568,0.0,0.0,0.0,0.6038,0.3962,1 419 | theverge.com,-0.2609,0.0682,0.4738,0.4438,0.0128,0.0014,1 420 | theweek.com,-0.1809,0.1754,0.1858,0.273,0.3507,0.0152,1 421 | thinkprogress.org,-0.8615,0.9498,0.0485,0.0014,0.0002,0.0,1 422 | threepercenternation.com,0.8465,0.0001,0.0,0.0013,0.5369,0.4618,1 423 | time.com,-0.3336,0.2594,0.3651,0.2387,0.1072,0.0298,1 424 | timesofisrael.com,0.3685,0.0125,0.044,0.3475,0.5743,0.0218,1 425 | today.com,-0.1668,0.0064,0.2203,0.7328,0.0387,0.0019,1 426 | topinfopost.com,-0.1502,0.0073,0.6837,0.2701,0.0347,0.0043,1 427 | toprightnews.com,0.8796,0.0,0.0,0.0,0.4225,0.5775,1 428 | townhall.com,0.9263,0.0002,0.0004,0.0009,0.1307,0.8678,1 429 | tpnn.com,0.9323,0.0,0.0,0.0,0.0198,0.9801,1 430 | trueactivist.com,-0.6032,0.0135,0.2341,0.0566,0.6958,0.0,1 431 | truth-out.org,-0.8937,0.8042,0.1917,0.0037,0.0001,0.0002,1 432 | truthandaction.org,0.7952,0.0,0.0001,0.0008,0.7723,0.2268,1 433 | truthdig.com,-0.8565,0.799,0.1909,0.0091,0.0007,0.0003,1 434 | truthrevolt.org,0.8805,0.0006,0.0,0.0318,0.4558,0.5118,1 435 | truthuncensored.net,0.8463,0.0,0.0,0.0085,0.5336,0.4579,1 436 | twitchy.com,0.9375,0.0,0.0029,0.001,0.1177,0.8784,1 437 | twitter.com,-0.2177,0.4426,0.1053,0.1258,0.1201,0.2062,0 438 | tytnetwork.com,-0.7785,0.5193,0.4767,0.0036,0.0004,0.0,1 439 | ulstermanbooks.com,0.9456,0.0,0.0,0.0,0.0658,0.9342,1 440 | unitedwithisrael.org,0.5564,0.0001,0.0005,0.0445,0.9497,0.0052,1 441 | universalfreepress.com,0.8641,0.0,0.0015,0.0005,0.4119,0.5861,1 442 | uproxx.com,-0.4468,0.1885,0.6115,0.1867,0.0133,0.0,1 443 | upworthy.com,-0.8097,0.6771,0.3165,0.0064,0.0,0.0,1 444 | usatoday.com,-0.0635,0.0803,0.2209,0.515,0.165,0.0188,1 445 | usnews.com,-0.0392,0.0825,0.2029,0.1388,0.2019,0.3739,1 446 | valleycentral.com,0.0592,0.0404,0.1963,0.4897,0.2274,0.0463,1 447 | vice.com,-0.6267,0.2262,0.7134,0.042,0.0178,0.0006,1 448 | video.foxnews.com,0.838,0.001,0.002,0.0158,0.3087,0.6725,1 449 | video.lauraingraham.com,0.9419,0.0,0.0,0.0,0.0673,0.9327,1 450 | vimeo.com,-0.2916,0.4595,0.1619,0.0934,0.1376,0.1476,0 451 | viral.buzz,0.9176,0.0,0.0,0.0,0.0436,0.9564,1 452 | viralsurvival.com,0.813,0.0,0.0,0.0016,0.606,0.3923,1 453 | virtualjerusalem.com,0.512,0.0,0.0049,0.073,0.8998,0.0224,1 454 | voicesofliberty.com,0.4358,0.0002,0.0004,0.2866,0.7086,0.0041,1 455 | vox.com,-0.6591,0.5967,0.3334,0.0494,0.0198,0.0007,1 456 | warrior.scout.com,0.3947,0.0,0.0008,0.0553,0.9408,0.0031,1 457 | washington.cbslocal.com,0.3279,0.0311,0.0295,0.1414,0.4899,0.3081,1 458 | washingtonexaminer.com,0.82045,0.00155,0.0135,0.01075,0.33455,0.63965,1 459 | washingtonpost.com,-0.2568,0.2089,0.3615,0.2132,0.1598,0.0567,1 460 | washingtontimes.com,0.6975,0.0049,0.015,0.0267,0.473,0.4805,1 461 | wbaltv.com,-0.0221,0.034,0.2902,0.5514,0.1086,0.0159,1 462 | wcvb.com,-0.185,0.0272,0.3479,0.5806,0.0408,0.0034,1 463 | weaselzippers.us,1.0295,0.0,0.0002,0.0006,0.13,0.8692,1 464 | weeklystandard.com,0.9074,0.0004,0.0,0.0231,0.0985,0.8781,1 465 | westernjournalism.com,0.8991,0.0,0.0,0.0001,0.219,0.7808,1 466 | wfaa.com,0.1198,0.0148,0.047,0.5906,0.3393,0.0082,1 467 | wfla.com,0.041,0.006,0.0931,0.6402,0.2525,0.0082,1 468 | wfmz.com,-0.0973,0.0257,0.1756,0.6908,0.1002,0.0078,1 469 | wfsb.com,-0.1726,0.0205,0.4086,0.5298,0.0386,0.0026,1 470 | wftv.com,-0.2162,0.0233,0.4287,0.4862,0.0565,0.0053,1 471 | wgntv.com,-0.3593,0.0427,0.5848,0.2707,0.0994,0.0025,1 472 | whio.com,-0.0029,0.0104,0.1408,0.6881,0.1502,0.0105,1 473 | whitehouse.gov,-0.5325,0.4957,0.3248,0.1266,0.0499,0.003,1 474 | whnt.com,0.265,0.0006,0.017,0.1612,0.8152,0.006,1 475 | wired.com,-0.4027,0.0445,0.6135,0.31,0.0258,0.0061,1 476 | wjla.com,-0.3195,0.0871,0.4446,0.3086,0.1435,0.0162,1 477 | wmur.com,0.098,0.0767,0.0543,0.7367,0.1209,0.0113,1 478 | wnd.com,0.9013,0.0,0.0,0.0003,0.264,0.7357,1 479 | wnep.com,-0.0328,0.0125,0.1014,0.7843,0.0988,0.003,1 480 | worldstarhiphop.com,-0.7047,0.4041,0.5942,0.001,0.0006,0.0,1 481 | worldtruth.tv,-0.0491,0.001,0.0986,0.8306,0.0697,0.0001,1 482 | woundedamericanwarrior.com,0.8614,0.0,0.0,0.001,0.5539,0.4451,1 483 | wpxi.com,-0.2221,0.0465,0.2302,0.6782,0.0424,0.0027,1 484 | wral.com,-0.0685,0.1767,0.2693,0.3081,0.2208,0.0251,1 485 | wsbtv.com,-0.0872,0.0247,0.2159,0.5769,0.1715,0.011,1 486 | wsfa.com,0.1107,0.0189,0.1382,0.419,0.4082,0.0157,1 487 | wsj.com,0.2754,0.0101,0.1253,0.1632,0.6209,0.0805,1 488 | wtsp.com,-0.0038,0.028,0.306,0.5243,0.1213,0.0205,1 489 | wtvr.com,-0.0734,0.0691,0.153,0.7082,0.0661,0.0037,1 490 | wusa9.com,-0.4447,0.0902,0.5828,0.2755,0.0515,0.0,1 491 | wxyz.com,-0.3539,0.0662,0.3532,0.5462,0.033,0.0015,1 492 | ynetnews.com,0.3335,0.0229,0.146,0.3353,0.4418,0.0539,1 493 | youngcons.com,0.9684999999999999,0.0,0.0,0.0,0.1725,0.8274999999999999,1 494 | yournewswire.com,-0.2572,0.04,0.3849,0.4454,0.1222,0.0075,1 495 | youtube.com,0.0634,0.1533,0.2184,0.1947,0.2606,0.173,0 496 | zerohedge.com,0.4721,0.0032,0.0218,0.2158,0.5655,0.1936,1 497 | -------------------------------------------------------------------------------- /data/domain_coding/data/Domain Codings.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gitronald/domains/39a6f5488764b8a85685df278191c73269997adf/data/domain_coding/data/Domain Codings.xlsx -------------------------------------------------------------------------------- /data/domain_coding/data/black_sites.txt: -------------------------------------------------------------------------------- 1 | 12minutos.com 2 | 16wmpo.com 3 | 20minutenews.com 4 | 247newsmedia.com 5 | 24aktuelles.com 6 | 24online.news 7 | 24usainfo.com 8 | 24wpn.com 9 | abcnews.com.co 10 | actualite.co 11 | actualites.co 12 | adobochronicles.com 13 | alabamaobserver.com 14 | aldipest.com 15 | alertchild.com 16 | alynews.com 17 | americafans.com 18 | americanflare.com 19 | americanflavor.news 20 | americanjournalreview.com 21 | americanpeoplenetwork.com 22 | americanpoliticnews.co 23 | americanpresident.co 24 | americanprides.com 25 | americasnewest.com 26 | amposts.com 27 | anews-24.com 28 | anews24.org 29 | angrypatriotmovement.com 30 | anonjekloy.tk 31 | areyouasleep.com 32 | asamericanasapplepie.org 33 | associatedmediacoverage.com 34 | aurora-news.us 35 | badcriminals.com 36 | baldwinpost.com 37 | baltimoregazette.com 38 | battypost.com 39 | bb4sp.com 40 | beforeitsnews.com 41 | belgique.actualites.co 42 | bients.com 43 | bigbluevision.org 44 | bignuggetnews.com 45 | bizstandardnews.com 46 | bluevision.news 47 | bluevisionpost.com 48 | borderherald.com 49 | bostonleader.com 50 | breakingtop.world 51 | burrardstreetjournal.com 52 | butthatsnoneofmybusiness.com 53 | buzzfeedusa.com 54 | cartelpress.com 55 | cartelreport.com 56 | celebtricity.com 57 | channel16news.com 58 | channel17news.com 59 | channel18news.com 60 | channel22news.com 61 | channel23news.com 62 | channel28news.com 63 | channel34news.com 64 | channel45news.com 65 | channel5000.com 66 | choiceandtruth.com 67 | christiantimesnewspaper.com 68 | christiantoday.info 69 | chuckcallesto.blogspot.com 70 | civictribune.com 71 | clancyreport.com 72 | clashdaily.com 73 | clear-politics.com 74 | cnn.com.de 75 | cnnews3.com 76 | consciouslyenlightened.com 77 | conservativearmy88.com 78 | conservativedailypost.com 79 | conservativeflashnews.com 80 | conservativeinfocorner.com 81 | conservativeinsider.co 82 | conservativespirit.com 83 | conservativestudio.com 84 | consnation.com 85 | cooltobeconservative.com 86 | daily-sun.com 87 | dailycurrant.com 88 | dailyfinesser.com 89 | dailyinfobox.com 90 | dailyinsidernews.com 91 | dailynews10.com 92 | dailynews11.com 93 | dailynews3.com 94 | dailynews33.com 95 | dailynews5.com 96 | dailynewsposts.info 97 | dailyoccupation.com 98 | dailypresser.com 99 | dailysurge.com 100 | dailyusaupdate.com 101 | damnleaks.com 102 | democraticmoms.com 103 | denverguardian.com 104 | denverinquirer.com 105 | departed.co 106 | departedmedia.com 107 | dineal.com 108 | disclose.tv 109 | diyhours.net 110 | donaldtrumpnews.co 111 | donaldtrumppotus45.com 112 | drugsofficial.com 113 | embols.com 114 | empireherald.com 115 | empirenews.net 116 | empiresports.co 117 | en-volve.com 118 | en.mediamass.net 119 | endingthefed.com 120 | enhlive.com 121 | everydaybreakingnews.com 122 | everynewshere.com 123 | famousviralstories.com 124 | fanzinger.com 125 | federalistnation.com 126 | federalisttribune.com 127 | fedsalert.com 128 | flashinfo.org 129 | flashnewscorner.com 130 | floridasunpost.com 131 | focusnews.info 132 | folksvideo.com 133 | fox-news24.com 134 | france.actualites.co 135 | freddymag.com 136 | freedomcrossroads.us 137 | freedomdaily.com 138 | freedomsfinalstand.com 139 | freshdailyreport.com 140 | friendsofsyria.wordpress.com 141 | givemeliberty01.com 142 | globalassociatednews.com 143 | globalpoliticsnow.com 144 | greenvillegazette.com 145 | guerilla.news 146 | guerillanews.com 147 | gummypost.com 148 | halturnershow.com 149 | headlinebrief.com 150 | healthyworldhouse.com 151 | heaviermetal.net 152 | hotglobalnews.com 153 | houstonchronicle-tv.com 154 | huzlers.com 155 | ilovemyfreedom.org 156 | interestingdailynews.com 157 | intrendtoday.com 158 | ipatriot.com 159 | isthatlegit.com 160 | jokerviral.com 161 | kata33.com 162 | klponews.com 163 | km8news.com 164 | kmt11.com 165 | knp7.com 166 | konkonsagh.biz 167 | krbcnews.com 168 | kspm33.com 169 | kupr7.com 170 | ky12news.com 171 | ky6news.com 172 | kypo6.com 173 | ladylibertysnews.com 174 | landrypost.com 175 | lastdeplorables.com 176 | liberalplug.com 177 | liberty-courier.com 178 | libertyalliance.com 179 | libertywritersnews.com 180 | local31news.com 181 | localnews33.com 182 | londonwebnews.com 183 | lopezreport.com 184 | madworldnews.com 185 | mainerepublicemailalert.com 186 | majorthoughts.com 187 | maywoodpost.com 188 | mbynews.com 189 | mckenziepost.com 190 | mediazone.news 191 | metropolitanworlds.com 192 | mississippiherald.com 193 | morningnewsusa.com 194 | mrnewswatch.com 195 | msfanpage.link 196 | msnbc.website 197 | nationalinsiderpolitics.com 198 | nationalreport.net 199 | nbc.com.co 200 | ncscooper.com 201 | neonnettle.com 202 | nephef.com 203 | nevo.news 204 | newpoliticstoday.com 205 | news14kgpn.com 206 | news14now.com 207 | news4ktla.com 208 | newsbiscuit.com 209 | newsbreakingspipe.com 210 | newsbreakshere.com 211 | newsbuzzdaily.com 212 | newsbysquad.com 213 | newsdaily10.com 214 | newsdaily12.com 215 | newsdaily27.com 216 | newsexaminer.net 217 | newsfeedhunter.com 218 | newsfeedobserver.com 219 | newshubs.info 220 | newsjustforyou1.blogspot.com 221 | newsleak.co 222 | newslo.com 223 | newsnow17.com 224 | newswatch33.com 225 | newzmagazine.com 226 | notallowedto.com 227 | noticias365.info 228 | now8news.com 229 | nymeta.co 230 | occupydemocrats.com 231 | onepoliticalplaza.com 232 | openmagazines.com 233 | oreillypost.com 234 | ourlandofthefree.com 235 | paris.actualites.co 236 | patriothangout.com 237 | persecutes.com 238 | politicops.com 239 | politicot.com 240 | politicsusanews.com 241 | powerdaily.us 242 | president45donaldtrump.com 243 | pressunion.org 244 | prntly.com 245 | proudleader.com 246 | qualitysharing.com 247 | react365.com 248 | readconservatives.news 249 | realnewsrightnow.com 250 | redcountry.us 251 | redinfo.us 252 | redrocktribune.com 253 | redstatewatcher.com 254 | religionmind.com 255 | rickwells.us 256 | rilenews.com 257 | rogue-nation3.com 258 | rumorjournal.com 259 | satiratribune.com 260 | scrapetv.com 261 | smhwtfnews.com 262 | snoopack.com 263 | socialeverythings.com 264 | southernconservativeextra.com 265 | spinzon.com 266 | statenation.co 267 | states-tv.com 268 | stgeorgegazette.com 269 | straightstoned.com 270 | stuppid.com 271 | success-street.com 272 | supremepatriot.com 273 | tdnewswire.com 274 | tdtalliance.com 275 | teddystick.com 276 | telegraphsun.com 277 | the-insider.co 278 | the-postillon.com 279 | theavocadonews.com 280 | thebostontribune.com 281 | thebreakingnews.co 282 | theexaminer.site 283 | thefrt.com 284 | theinternationalreporter.org 285 | theinternetpost.net 286 | thelastlineofdefense.org 287 | themoralofthestory.us 288 | thenationalsun.com 289 | thenet24h.com 290 | thenewsnerd.com 291 | thenewyorkevening.com 292 | thenochill.com 293 | thepoliticaltribune.com 294 | thepremiumnews.com 295 | theracketreport.com 296 | thereporterz.com 297 | therightists.com 298 | theseattletribune.com 299 | thetrumpmedia.com 300 | theusa-news.com 301 | theusaconservative.com 302 | thevalleyreport.com 303 | thewashingtonpress.com 304 | times.com.mx 305 | tmzbreaking.com 306 | tmzbusiness.com 307 | tmzcomedy.com 308 | tmzhiphop.com 309 | tmzuncut.com 310 | tmzurban.com 311 | tmzworldnews.com 312 | tmzworldstarnews.com 313 | trueamericans.me 314 | truetrumpers.com 315 | truthkings.com 316 | undergroundnewsreport.com 317 | unitedmediapublishing.com 318 | universepolitics.com 319 | usa-conservative.com 320 | usa-radio.com 321 | usa-television.com 322 | usadailyinfo.com 323 | usadailypost.us 324 | usadailytime.com 325 | usadosenews.com 326 | usafirstinformation.com 327 | usanews4u.us 328 | usanewsflash.com 329 | usanewshome.com 330 | usanewstoday.com 331 | usapolitics24hrs.com 332 | usapoliticsnow.com 333 | usapoliticstoday.com 334 | usapoliticszone.com 335 | usasnich.com 336 | usatodaynews.me 337 | usatodaypolitics.com 338 | usaworldbox.com 339 | ushealthyadvisor.com 340 | ushealthylife.com 341 | usherald.com 342 | usinfonews.com 343 | uspoln.com 344 | uspostman.com 345 | vesselnews.io 346 | viralactions.com 347 | viralcocaine.com 348 | viralcords.com 349 | viraldevil.com 350 | viralmugshot.com 351 | viralpropaganda.com 352 | viralspeech.com 353 | viralstuppid.com 354 | voxtribune.com 355 | washingtonevening.com 356 | washingtonfeed.com 357 | washingtonpost.com.co 358 | wazanews.tk 359 | wcpm3.com 360 | weconservative.com 361 | weekendherald.com 362 | wetheproudpatriots.com 363 | wftj8news.com 364 | whatsupic.com 365 | witscience.org 366 | wleb21.com 367 | wm21news.com 368 | wmacnews.com 369 | wmb36.com 370 | world-politicus.com 371 | worldinformation24.info 372 | worldnewsdailyreport.com 373 | worldnewspolitics.com 374 | worldpoliticsnow.com 375 | worldpoliticus.com 376 | wrejnews.com 377 | wrpt16.com 378 | wtoe5news.com 379 | xbn-news.com 380 | yesimright.com 381 | yournewswire.com 382 | zootfeed.com 383 | -------------------------------------------------------------------------------- /data/domain_coding/data/website_alignment_scores.xlsx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/gitronald/domains/39a6f5488764b8a85685df278191c73269997adf/data/domain_coding/data/website_alignment_scores.xlsx -------------------------------------------------------------------------------- /data/domain_coding/grinberg2019.tsv: -------------------------------------------------------------------------------- 1 | domain fn_color fn_is_fake 2 | afp.com green 0.0 3 | buzzfeed.com green 0.0 4 | dallasnews.com green 0.0 5 | dw.com green 0.0 6 | foxnews.com green 0.0 7 | huffingtonpost.com green 0.0 8 | ijr.com green 0.0 9 | independent.co.uk green 0.0 10 | lawofficer.com green 0.0 11 | magicvalley.com green 0.0 12 | montgomeryadvertiser.com green 0.0 13 | msn.com green 0.0 14 | newsday.com green 0.0 15 | talkingpointsmemo.com green 0.0 16 | telegraph.co.uk green 0.0 17 | time.com green 0.0 18 | washingtontimes.com green 0.0 19 | yahoo.com green 0.0 20 | amazon.com 0.0 21 | ebay.com 0.0 22 | etsy.com 0.0 23 | facebook.com 0.0 24 | flickr.com 0.0 25 | google.com 0.0 26 | hillaryspeeches.com 0.0 27 | imgur.com 0.0 28 | instagram.com 0.0 29 | legacy.com 0.0 30 | linkis.com 0.0 31 | princeton.edu 0.0 32 | sli.mg 0.0 33 | yelp.com 0.0 34 | youtube.com 0.0 35 | 2ndvote.com orange 1.0 36 | afa.net orange 1.0 37 | ahtribune.com orange 1.0 38 | awarenessact.com orange 1.0 39 | concealednation.org orange 1.0 40 | conservativetribune.com orange 1.0 41 | crooksandliars.com orange 1.0 42 | dailycaller.com orange 1.0 43 | dailyheadlines.net orange 1.0 44 | dailynewsbin.com orange 1.0 45 | dailypost.ng orange 1.0 46 | dailywire.com orange 1.0 47 | davidwolfe.com orange 1.0 48 | defund.com orange 1.0 49 | dennismichaellynch.com orange 1.0 50 | endoftheamericandream.com orange 1.0 51 | express.co.uk orange 1.0 52 | healthnutnews.com orange 1.0 53 | heatst.com orange 1.0 54 | impulsetoday.com orange 1.0 55 | inquisitr.com orange 1.0 56 | iotwreport.com orange 1.0 57 | joeforamerica.com orange 1.0 58 | medicalkidnap.com orange 1.0 59 | newcenturytimes.com orange 1.0 60 | onlysimchas.com orange 1.0 61 | palmerreport.com orange 1.0 62 | pamelageller.com orange 1.0 63 | qpolitical.com orange 1.0 64 | redflagnews.com orange 1.0 65 | regated.com orange 1.0 66 | rightwingnews.com orange 1.0 67 | theconservativetreehouse.com orange 1.0 68 | thefederalistpapers.org orange 1.0 69 | thehornnews.com orange 1.0 70 | themindunleashed.com orange 1.0 71 | thenationalpatriot.com orange 1.0 72 | tmn.today orange 1.0 73 | toprightnews.com orange 1.0 74 | tribunist.com orange 1.0 75 | trueactivist.com orange 1.0 76 | uschronicle.com orange 1.0 77 | youngcons.com orange 1.0 78 | zerohedge.com orange 1.0 79 | usuncut.com orange 1.0 80 | chicksontheright.com orange 1.0 81 | ihavethetruth.com orange 1.0 82 | 100percentfedup.com red 1.0 83 | activistpost.com red 1.0 84 | allenbwest.com red 1.0 85 | americannews.com red 1.0 86 | americantoday.news red 1.0 87 | americasfreedomfighters.com red 1.0 88 | anonews.co red 1.0 89 | anonhq.com red 1.0 90 | barenakedislam.com red 1.0 91 | bipartisanreport.com red 1.0 92 | channel-7-news.com red 1.0 93 | collective-evolution.com red 1.0 94 | conservativefiringline.com red 1.0 95 | conservativeoutfitters.com red 1.0 96 | conservativepost.com red 1.0 97 | dailystormer.com red 1.0 98 | dcclothesline.com red 1.0 99 | downtrend.com red 1.0 100 | endtimeheadlines.org red 1.0 101 | eutimes.net red 1.0 102 | fellowshipoftheminds.com red 1.0 103 | frontpagemag.com red 1.0 104 | fury.news red 1.0 105 | getoffthebs.com red 1.0 106 | gopthedailydose.com red 1.0 107 | gotnews.com red 1.0 108 | infowars.com red 1.0 109 | jookos.com red 1.0 110 | judicialwatch.org red 1.0 111 | louderwithcrowder.com red 1.0 112 | myfreshnews.com red 1.0 113 | naturalnews.com red 1.0 114 | newsrescue.com red 1.0 115 | nowtheendbegins.com red 1.0 116 | observatorial.com red 1.0 117 | powderedwigsociety.com red 1.0 118 | religiousmind.com red 1.0 119 | rightsidenews.com red 1.0 120 | shariaunveiled.wordpress.com red 1.0 121 | sourceplanet.net red 1.0 122 | stateofthenation2012.com red 1.0 123 | superstation95.com red 1.0 124 | theeventchronicle.com red 1.0 125 | thefreepatriot.org red 1.0 126 | thegatewaypundit.com red 1.0 127 | thelastamericanvagabond.com red 1.0 128 | thenewsclub.info red 1.0 129 | trunews.com red 1.0 130 | truthfeed.com red 1.0 131 | truthuncensored.net red 1.0 132 | usasupreme.com red 1.0 133 | viralliberty.com red 1.0 134 | wearechange.org red 1.0 135 | westernsentinel.com red 1.0 136 | whatdoesitmean.com red 1.0 137 | wnd.com red 1.0 138 | worldtruth.tv red 1.0 139 | eaglerising.com red 1.0 140 | proudcons.com red 1.0 141 | allenwestrepublic.com red 1.0 142 | conservativebyte.com red 1.0 143 | babylonbee.com satire 0.0 144 | freewoodpost.com satire 0.0 145 | realtruenews.org satire 0.0 146 | thebeaverton.com satire 0.0 147 | thedailymash.co.uk satire 0.0 148 | addictinginfo.org yellow 0.0 149 | awm.com yellow 0.0 150 | blakkpepper.com yellow 0.0 151 | breitbart.com yellow 0.0 152 | cheezburger.com yellow 0.0 153 | christiannews.net yellow 0.0 154 | cosmopolitan.com yellow 0.0 155 | dailykos.com yellow 0.0 156 | dailymail.co.uk yellow 0.0 157 | deadstate.org yellow 0.0 158 | hellochristian.com yellow 0.0 159 | hinterlandgazette.com yellow 0.0 160 | hngn.com yellow 0.0 161 | lifenews.com yellow 0.0 162 | lifesitenews.com yellow 0.0 163 | metalsucks.net yellow 0.0 164 | metro.co.uk yellow 0.0 165 | nypost.com yellow 0.0 166 | redstate.com yellow 0.0 167 | standard.co.uk yellow 0.0 168 | thefederalist.com yellow 0.0 169 | theintellectualist.co yellow 0.0 170 | thesun.co.uk yellow 0.0 171 | tmz.com yellow 0.0 172 | 12minutos.com black 1.0 173 | 16wmpo.com black 1.0 174 | 20minutenews.com black 1.0 175 | 247newsmedia.com black 1.0 176 | 24aktuelles.com black 1.0 177 | 24online.news black 1.0 178 | 24usainfo.com black 1.0 179 | 24wpn.com black 1.0 180 | abcnews.com.co black 1.0 181 | actualite.co black 1.0 182 | actualites.co black 1.0 183 | adobochronicles.com black 1.0 184 | alabamaobserver.com black 1.0 185 | aldipest.com black 1.0 186 | alertchild.com black 1.0 187 | alynews.com black 1.0 188 | americafans.com black 1.0 189 | americanflare.com black 1.0 190 | americanflavor.news black 1.0 191 | americanjournalreview.com black 1.0 192 | americanpeoplenetwork.com black 1.0 193 | americanpoliticnews.co black 1.0 194 | americanpresident.co black 1.0 195 | americanprides.com black 1.0 196 | americasnewest.com black 1.0 197 | amposts.com black 1.0 198 | anews-24.com black 1.0 199 | anews24.org black 1.0 200 | angrypatriotmovement.com black 1.0 201 | anonjekloy.tk black 1.0 202 | areyouasleep.com black 1.0 203 | asamericanasapplepie.org black 1.0 204 | associatedmediacoverage.com black 1.0 205 | aurora-news.us black 1.0 206 | badcriminals.com black 1.0 207 | baldwinpost.com black 1.0 208 | baltimoregazette.com black 1.0 209 | battypost.com black 1.0 210 | bb4sp.com black 1.0 211 | beforeitsnews.com black 1.0 212 | belgique.actualites.co black 1.0 213 | bients.com black 1.0 214 | bigbluevision.org black 1.0 215 | bignuggetnews.com black 1.0 216 | bizstandardnews.com black 1.0 217 | bluevision.news black 1.0 218 | bluevisionpost.com black 1.0 219 | borderherald.com black 1.0 220 | bostonleader.com black 1.0 221 | breakingtop.world black 1.0 222 | burrardstreetjournal.com black 1.0 223 | butthatsnoneofmybusiness.com black 1.0 224 | buzzfeedusa.com black 1.0 225 | cartelpress.com black 1.0 226 | cartelreport.com black 1.0 227 | celebtricity.com black 1.0 228 | channel16news.com black 1.0 229 | channel17news.com black 1.0 230 | channel18news.com black 1.0 231 | channel22news.com black 1.0 232 | channel23news.com black 1.0 233 | channel28news.com black 1.0 234 | channel34news.com black 1.0 235 | channel45news.com black 1.0 236 | channel5000.com black 1.0 237 | choiceandtruth.com black 1.0 238 | christiantimesnewspaper.com black 1.0 239 | christiantoday.info black 1.0 240 | chuckcallesto.blogspot.com black 1.0 241 | civictribune.com black 1.0 242 | clancyreport.com black 1.0 243 | clashdaily.com black 1.0 244 | clear-politics.com black 1.0 245 | cnn.com.de black 1.0 246 | cnnews3.com black 1.0 247 | consciouslyenlightened.com black 1.0 248 | conservativearmy88.com black 1.0 249 | conservativedailypost.com black 1.0 250 | conservativeflashnews.com black 1.0 251 | conservativeinfocorner.com black 1.0 252 | conservativeinsider.co black 1.0 253 | conservativespirit.com black 1.0 254 | conservativestudio.com black 1.0 255 | consnation.com black 1.0 256 | cooltobeconservative.com black 1.0 257 | daily-sun.com black 1.0 258 | dailycurrant.com black 1.0 259 | dailyfinesser.com black 1.0 260 | dailyinfobox.com black 1.0 261 | dailyinsidernews.com black 1.0 262 | dailynews10.com black 1.0 263 | dailynews11.com black 1.0 264 | dailynews3.com black 1.0 265 | dailynews33.com black 1.0 266 | dailynews5.com black 1.0 267 | dailynewsposts.info black 1.0 268 | dailyoccupation.com black 1.0 269 | dailypresser.com black 1.0 270 | dailysurge.com black 1.0 271 | dailyusaupdate.com black 1.0 272 | damnleaks.com black 1.0 273 | democraticmoms.com black 1.0 274 | denverguardian.com black 1.0 275 | denverinquirer.com black 1.0 276 | departed.co black 1.0 277 | departedmedia.com black 1.0 278 | dineal.com black 1.0 279 | disclose.tv black 1.0 280 | diyhours.net black 1.0 281 | donaldtrumpnews.co black 1.0 282 | donaldtrumppotus45.com black 1.0 283 | drugsofficial.com black 1.0 284 | embols.com black 1.0 285 | empireherald.com black 1.0 286 | empirenews.net black 1.0 287 | empiresports.co black 1.0 288 | en-volve.com black 1.0 289 | en.mediamass.net black 1.0 290 | endingthefed.com black 1.0 291 | enhlive.com black 1.0 292 | everydaybreakingnews.com black 1.0 293 | everynewshere.com black 1.0 294 | famousviralstories.com black 1.0 295 | fanzinger.com black 1.0 296 | federalistnation.com black 1.0 297 | federalisttribune.com black 1.0 298 | fedsalert.com black 1.0 299 | flashinfo.org black 1.0 300 | flashnewscorner.com black 1.0 301 | floridasunpost.com black 1.0 302 | focusnews.info black 1.0 303 | folksvideo.com black 1.0 304 | fox-news24.com black 1.0 305 | france.actualites.co black 1.0 306 | freddymag.com black 1.0 307 | freedomcrossroads.us black 1.0 308 | freedomdaily.com black 1.0 309 | freedomsfinalstand.com black 1.0 310 | freshdailyreport.com black 1.0 311 | friendsofsyria.wordpress.com black 1.0 312 | givemeliberty01.com black 1.0 313 | globalassociatednews.com black 1.0 314 | globalpoliticsnow.com black 1.0 315 | greenvillegazette.com black 1.0 316 | guerilla.news black 1.0 317 | guerillanews.com black 1.0 318 | gummypost.com black 1.0 319 | halturnershow.com black 1.0 320 | headlinebrief.com black 1.0 321 | healthyworldhouse.com black 1.0 322 | heaviermetal.net black 1.0 323 | hotglobalnews.com black 1.0 324 | houstonchronicle-tv.com black 1.0 325 | huzlers.com black 1.0 326 | ilovemyfreedom.org black 1.0 327 | interestingdailynews.com black 1.0 328 | intrendtoday.com black 1.0 329 | ipatriot.com black 1.0 330 | isthatlegit.com black 1.0 331 | jokerviral.com black 1.0 332 | kata33.com black 1.0 333 | klponews.com black 1.0 334 | km8news.com black 1.0 335 | kmt11.com black 1.0 336 | knp7.com black 1.0 337 | konkonsagh.biz black 1.0 338 | krbcnews.com black 1.0 339 | kspm33.com black 1.0 340 | kupr7.com black 1.0 341 | ky12news.com black 1.0 342 | ky6news.com black 1.0 343 | kypo6.com black 1.0 344 | ladylibertysnews.com black 1.0 345 | landrypost.com black 1.0 346 | lastdeplorables.com black 1.0 347 | liberalplug.com black 1.0 348 | liberty-courier.com black 1.0 349 | libertyalliance.com black 1.0 350 | libertywritersnews.com black 1.0 351 | local31news.com black 1.0 352 | localnews33.com black 1.0 353 | londonwebnews.com black 1.0 354 | lopezreport.com black 1.0 355 | madworldnews.com black 1.0 356 | mainerepublicemailalert.com black 1.0 357 | majorthoughts.com black 1.0 358 | maywoodpost.com black 1.0 359 | mbynews.com black 1.0 360 | mckenziepost.com black 1.0 361 | mediazone.news black 1.0 362 | metropolitanworlds.com black 1.0 363 | mississippiherald.com black 1.0 364 | morningnewsusa.com black 1.0 365 | mrnewswatch.com black 1.0 366 | msfanpage.link black 1.0 367 | msnbc.website black 1.0 368 | nationalinsiderpolitics.com black 1.0 369 | nationalreport.net black 1.0 370 | nbc.com.co black 1.0 371 | ncscooper.com black 1.0 372 | neonnettle.com black 1.0 373 | nephef.com black 1.0 374 | nevo.news black 1.0 375 | newpoliticstoday.com black 1.0 376 | news14kgpn.com black 1.0 377 | news14now.com black 1.0 378 | news4ktla.com black 1.0 379 | newsbiscuit.com black 1.0 380 | newsbreakingspipe.com black 1.0 381 | newsbreakshere.com black 1.0 382 | newsbuzzdaily.com black 1.0 383 | newsbysquad.com black 1.0 384 | newsdaily10.com black 1.0 385 | newsdaily12.com black 1.0 386 | newsdaily27.com black 1.0 387 | newsexaminer.net black 1.0 388 | newsfeedhunter.com black 1.0 389 | newsfeedobserver.com black 1.0 390 | newshubs.info black 1.0 391 | newsjustforyou1.blogspot.com black 1.0 392 | newsleak.co black 1.0 393 | newslo.com black 1.0 394 | newsnow17.com black 1.0 395 | newswatch33.com black 1.0 396 | newzmagazine.com black 1.0 397 | notallowedto.com black 1.0 398 | noticias365.info black 1.0 399 | now8news.com black 1.0 400 | nymeta.co black 1.0 401 | occupydemocrats.com black 1.0 402 | onepoliticalplaza.com black 1.0 403 | openmagazines.com black 1.0 404 | oreillypost.com black 1.0 405 | ourlandofthefree.com black 1.0 406 | paris.actualites.co black 1.0 407 | patriothangout.com black 1.0 408 | persecutes.com black 1.0 409 | politicops.com black 1.0 410 | politicot.com black 1.0 411 | politicsusanews.com black 1.0 412 | powerdaily.us black 1.0 413 | president45donaldtrump.com black 1.0 414 | pressunion.org black 1.0 415 | prntly.com black 1.0 416 | proudleader.com black 1.0 417 | qualitysharing.com black 1.0 418 | react365.com black 1.0 419 | readconservatives.news black 1.0 420 | realnewsrightnow.com black 1.0 421 | redcountry.us black 1.0 422 | redinfo.us black 1.0 423 | redrocktribune.com black 1.0 424 | redstatewatcher.com black 1.0 425 | religionmind.com black 1.0 426 | rickwells.us black 1.0 427 | rilenews.com black 1.0 428 | rogue-nation3.com black 1.0 429 | rumorjournal.com black 1.0 430 | satiratribune.com black 1.0 431 | scrapetv.com black 1.0 432 | smhwtfnews.com black 1.0 433 | snoopack.com black 1.0 434 | socialeverythings.com black 1.0 435 | southernconservativeextra.com black 1.0 436 | spinzon.com black 1.0 437 | statenation.co black 1.0 438 | states-tv.com black 1.0 439 | stgeorgegazette.com black 1.0 440 | straightstoned.com black 1.0 441 | stuppid.com black 1.0 442 | success-street.com black 1.0 443 | supremepatriot.com black 1.0 444 | tdnewswire.com black 1.0 445 | tdtalliance.com black 1.0 446 | teddystick.com black 1.0 447 | telegraphsun.com black 1.0 448 | the-insider.co black 1.0 449 | the-postillon.com black 1.0 450 | theavocadonews.com black 1.0 451 | thebostontribune.com black 1.0 452 | thebreakingnews.co black 1.0 453 | theexaminer.site black 1.0 454 | thefrt.com black 1.0 455 | theinternationalreporter.org black 1.0 456 | theinternetpost.net black 1.0 457 | thelastlineofdefense.org black 1.0 458 | themoralofthestory.us black 1.0 459 | thenationalsun.com black 1.0 460 | thenet24h.com black 1.0 461 | thenewsnerd.com black 1.0 462 | thenewyorkevening.com black 1.0 463 | thenochill.com black 1.0 464 | thepoliticaltribune.com black 1.0 465 | thepremiumnews.com black 1.0 466 | theracketreport.com black 1.0 467 | thereporterz.com black 1.0 468 | therightists.com black 1.0 469 | theseattletribune.com black 1.0 470 | thetrumpmedia.com black 1.0 471 | theusa-news.com black 1.0 472 | theusaconservative.com black 1.0 473 | thevalleyreport.com black 1.0 474 | thewashingtonpress.com black 1.0 475 | times.com.mx black 1.0 476 | tmzbreaking.com black 1.0 477 | tmzbusiness.com black 1.0 478 | tmzcomedy.com black 1.0 479 | tmzhiphop.com black 1.0 480 | tmzuncut.com black 1.0 481 | tmzurban.com black 1.0 482 | tmzworldnews.com black 1.0 483 | tmzworldstarnews.com black 1.0 484 | trueamericans.me black 1.0 485 | truetrumpers.com black 1.0 486 | truthkings.com black 1.0 487 | undergroundnewsreport.com black 1.0 488 | unitedmediapublishing.com black 1.0 489 | universepolitics.com black 1.0 490 | usa-conservative.com black 1.0 491 | usa-radio.com black 1.0 492 | usa-television.com black 1.0 493 | usadailyinfo.com black 1.0 494 | usadailypost.us black 1.0 495 | usadailytime.com black 1.0 496 | usadosenews.com black 1.0 497 | usafirstinformation.com black 1.0 498 | usanews4u.us black 1.0 499 | usanewsflash.com black 1.0 500 | usanewshome.com black 1.0 501 | usanewstoday.com black 1.0 502 | usapolitics24hrs.com black 1.0 503 | usapoliticsnow.com black 1.0 504 | usapoliticstoday.com black 1.0 505 | usapoliticszone.com black 1.0 506 | usasnich.com black 1.0 507 | usatodaynews.me black 1.0 508 | usatodaypolitics.com black 1.0 509 | usaworldbox.com black 1.0 510 | ushealthyadvisor.com black 1.0 511 | ushealthylife.com black 1.0 512 | usherald.com black 1.0 513 | usinfonews.com black 1.0 514 | uspoln.com black 1.0 515 | uspostman.com black 1.0 516 | vesselnews.io black 1.0 517 | viralactions.com black 1.0 518 | viralcocaine.com black 1.0 519 | viralcords.com black 1.0 520 | viraldevil.com black 1.0 521 | viralmugshot.com black 1.0 522 | viralpropaganda.com black 1.0 523 | viralspeech.com black 1.0 524 | viralstuppid.com black 1.0 525 | voxtribune.com black 1.0 526 | washingtonevening.com black 1.0 527 | washingtonfeed.com black 1.0 528 | washingtonpost.com.co black 1.0 529 | wazanews.tk black 1.0 530 | wcpm3.com black 1.0 531 | weconservative.com black 1.0 532 | weekendherald.com black 1.0 533 | wetheproudpatriots.com black 1.0 534 | wftj8news.com black 1.0 535 | whatsupic.com black 1.0 536 | witscience.org black 1.0 537 | wleb21.com black 1.0 538 | wm21news.com black 1.0 539 | wmacnews.com black 1.0 540 | wmb36.com black 1.0 541 | world-politicus.com black 1.0 542 | worldinformation24.info black 1.0 543 | worldnewsdailyreport.com black 1.0 544 | worldnewspolitics.com black 1.0 545 | worldpoliticsnow.com black 1.0 546 | worldpoliticus.com black 1.0 547 | wrejnews.com black 1.0 548 | wrpt16.com black 1.0 549 | wtoe5news.com black 1.0 550 | xbn-news.com black 1.0 551 | yesimright.com black 1.0 552 | yournewswire.com black 1.0 553 | zootfeed.com black 1.0 554 | -------------------------------------------------------------------------------- /data/fake_news.tsv: -------------------------------------------------------------------------------- 1 | domain color is_fake 2 | afp.com green False 3 | buzzfeed.com green False 4 | dallasnews.com green False 5 | dw.com green False 6 | foxnews.com green False 7 | huffingtonpost.com green False 8 | ijr.com green False 9 | independent.co.uk green False 10 | lawofficer.com green False 11 | magicvalley.com green False 12 | montgomeryadvertiser.com green False 13 | msn.com green False 14 | newsday.com green False 15 | talkingpointsmemo.com green False 16 | telegraph.co.uk green False 17 | time.com green False 18 | washingtontimes.com green False 19 | yahoo.com green False 20 | amazon.com False 21 | ebay.com False 22 | etsy.com False 23 | facebook.com False 24 | flickr.com False 25 | google.com False 26 | hillaryspeeches.com False 27 | imgur.com False 28 | instagram.com False 29 | legacy.com False 30 | linkis.com False 31 | princeton.edu False 32 | sli.mg False 33 | yelp.com False 34 | youtube.com False 35 | 2ndvote.com orange True 36 | afa.net orange True 37 | ahtribune.com orange True 38 | awarenessact.com orange True 39 | concealednation.org orange True 40 | conservativetribune.com orange True 41 | crooksandliars.com orange True 42 | dailycaller.com orange True 43 | dailyheadlines.net orange True 44 | dailynewsbin.com orange True 45 | dailypost.ng orange True 46 | dailywire.com orange True 47 | davidwolfe.com orange True 48 | defund.com orange True 49 | dennismichaellynch.com orange True 50 | endoftheamericandream.com orange True 51 | express.co.uk orange True 52 | healthnutnews.com orange True 53 | heatst.com orange True 54 | impulsetoday.com orange True 55 | inquisitr.com orange True 56 | iotwreport.com orange True 57 | joeforamerica.com orange True 58 | medicalkidnap.com orange True 59 | newcenturytimes.com orange True 60 | onlysimchas.com orange True 61 | palmerreport.com orange True 62 | pamelageller.com orange True 63 | qpolitical.com orange True 64 | Redflagnews.com orange True 65 | regated.com orange True 66 | rightwingnews.com orange True 67 | theconservativetreehouse.com orange True 68 | thefederalistpapers.org orange True 69 | thehornnews.com orange True 70 | themindunleashed.com orange True 71 | thenationalpatriot.com orange True 72 | tmn.today orange True 73 | toprightnews.com orange True 74 | tribunist.com orange True 75 | trueactivist.com orange True 76 | uschronicle.com orange True 77 | youngcons.com orange True 78 | zerohedge.com orange True 79 | usuncut.com orange True 80 | chicksontheright.com orange True 81 | ihavethetruth.com orange True 82 | 100percentfedup.com red True 83 | activistpost.com red True 84 | allenbwest.com red True 85 | americannews.com red True 86 | americantoday.news red True 87 | americasfreedomfighters.com red True 88 | anonews.co red True 89 | anonhq.com red True 90 | barenakedislam.com red True 91 | bipartisanreport.com red True 92 | channel-7-news.com red True 93 | collective-evolution.com red True 94 | conservativefiringline.com red True 95 | conservativeoutfitters.com red True 96 | conservativepost.com red True 97 | dailystormer.com red True 98 | dcclothesline.com red True 99 | downtrend.com red True 100 | endtimeheadlines.org red True 101 | eutimes.net red True 102 | fellowshipoftheminds.com red True 103 | frontpagemag.com red True 104 | fury.news red True 105 | getoffthebs.com red True 106 | gopthedailydose.com red True 107 | gotnews.com red True 108 | infowars.com red True 109 | jookos.com red True 110 | judicialwatch.org red True 111 | louderwithcrowder.com red True 112 | myfreshnews.com red True 113 | naturalnews.com red True 114 | newsrescue.com red True 115 | nowtheendbegins.com red True 116 | observatorial.com red True 117 | powderedwigsociety.com red True 118 | religiousmind.com red True 119 | rightsidenews.com red True 120 | shariaunveiled.wordpress.com red True 121 | sourceplanet.net red True 122 | stateofthenation2012.com red True 123 | superstation95.com red True 124 | theeventchronicle.com red True 125 | thefreepatriot.org red True 126 | thegatewaypundit.com red True 127 | thelastamericanvagabond.com red True 128 | thenewsclub.info red True 129 | trunews.com red True 130 | truthfeed.com red True 131 | truthuncensoRed.net red True 132 | usasupreme.com red True 133 | viralliberty.com red True 134 | wearechange.org red True 135 | westernsentinel.com red True 136 | whatdoesitmean.com red True 137 | wnd.com red True 138 | worldtruth.tv red True 139 | eaglerising.com red True 140 | proudcons.com red True 141 | allenwestrepublic.com red True 142 | conservativebyte.com red True 143 | babylonbee.com satire False 144 | freewoodpost.com satire False 145 | realtruenews.org satire False 146 | thebeaverton.com satire False 147 | thedailymash.co.uk satire False 148 | addictinginfo.org yellow False 149 | awm.com yellow False 150 | blakkpepper.com yellow False 151 | breitbart.com yellow False 152 | cheezburger.com yellow False 153 | christiannews.net yellow False 154 | cosmopolitan.com yellow False 155 | dailykos.com yellow False 156 | dailymail.co.uk yellow False 157 | deadstate.org yellow False 158 | hellochristian.com yellow False 159 | hinterlandgazette.com yellow False 160 | hngn.com yellow False 161 | lifenews.com yellow False 162 | lifesitenews.com yellow False 163 | metalsucks.net yellow False 164 | metro.co.uk yellow False 165 | nypost.com yellow False 166 | Redstate.com yellow False 167 | standard.co.uk yellow False 168 | thefederalist.com yellow False 169 | theintellectualist.co yellow False 170 | thesun.co.uk yellow False 171 | tmz.com yellow False 172 | 12minutos.com black True 173 | 16wmpo.com black True 174 | 20minutenews.com black True 175 | 247newsmedia.com black True 176 | 24aktuelles.com black True 177 | 24online.news black True 178 | 24usainfo.com black True 179 | 24wpn.com black True 180 | abcnews.com.co black True 181 | actualite.co black True 182 | actualites.co black True 183 | adobochronicles.com black True 184 | alabamaobserver.com black True 185 | aldipest.com black True 186 | alertchild.com black True 187 | alynews.com black True 188 | americafans.com black True 189 | americanflare.com black True 190 | americanflavor.news black True 191 | americanjournalreview.com black True 192 | americanpeoplenetwork.com black True 193 | americanpoliticnews.co black True 194 | americanpresident.co black True 195 | americanprides.com black True 196 | americasnewest.com black True 197 | amposts.com black True 198 | anews-24.com black True 199 | anews24.org black True 200 | angrypatriotmovement.com black True 201 | anonjekloy.tk black True 202 | areyouasleep.com black True 203 | asamericanasapplepie.org black True 204 | associatedmediacoverage.com black True 205 | aurora-news.us black True 206 | badcriminals.com black True 207 | baldwinpost.com black True 208 | baltimoregazette.com black True 209 | battypost.com black True 210 | bb4sp.com black True 211 | beforeitsnews.com black True 212 | belgique.actualites.co black True 213 | bients.com black True 214 | bigbluevision.org black True 215 | bignuggetnews.com black True 216 | bizstandardnews.com black True 217 | bluevision.news black True 218 | bluevisionpost.com black True 219 | borderherald.com black True 220 | bostonleader.com black True 221 | breakingtop.world black True 222 | burrardstreetjournal.com black True 223 | butthatsnoneofmybusiness.com black True 224 | buzzfeedusa.com black True 225 | cartelpress.com black True 226 | cartelreport.com black True 227 | celebtricity.com black True 228 | channel16news.com black True 229 | channel17news.com black True 230 | channel18news.com black True 231 | channel22news.com black True 232 | channel23news.com black True 233 | channel28news.com black True 234 | channel34news.com black True 235 | channel45news.com black True 236 | channel5000.com black True 237 | choiceandtruth.com black True 238 | christiantimesnewspaper.com black True 239 | christiantoday.info black True 240 | chuckcallesto.blogspot.com black True 241 | civictribune.com black True 242 | clancyreport.com black True 243 | clashdaily.com black True 244 | clear-politics.com black True 245 | cnn.com.de black True 246 | cnnews3.com black True 247 | consciouslyenlightened.com black True 248 | conservativearmy88.com black True 249 | conservativedailypost.com black True 250 | conservativeflashnews.com black True 251 | conservativeinfocorner.com black True 252 | conservativeinsider.co black True 253 | conservativespirit.com black True 254 | conservativestudio.com black True 255 | consnation.com black True 256 | cooltobeconservative.com black True 257 | daily-sun.com black True 258 | dailycurrant.com black True 259 | dailyfinesser.com black True 260 | dailyinfobox.com black True 261 | dailyinsidernews.com black True 262 | dailynews10.com black True 263 | dailynews11.com black True 264 | dailynews3.com black True 265 | dailynews33.com black True 266 | dailynews5.com black True 267 | dailynewsposts.info black True 268 | dailyoccupation.com black True 269 | dailypresser.com black True 270 | dailysurge.com black True 271 | dailyusaupdate.com black True 272 | damnleaks.com black True 273 | democraticmoms.com black True 274 | denverguardian.com black True 275 | denverinquirer.com black True 276 | departed.co black True 277 | departedmedia.com black True 278 | dineal.com black True 279 | disclose.tv black True 280 | diyhours.net black True 281 | donaldtrumpnews.co black True 282 | donaldtrumppotus45.com black True 283 | drugsofficial.com black True 284 | embols.com black True 285 | empireherald.com black True 286 | empirenews.net black True 287 | empiresports.co black True 288 | en-volve.com black True 289 | en.mediamass.net black True 290 | endingthefed.com black True 291 | enhlive.com black True 292 | everydaybreakingnews.com black True 293 | everynewshere.com black True 294 | famousviralstories.com black True 295 | fanzinger.com black True 296 | federalistnation.com black True 297 | federalisttribune.com black True 298 | fedsalert.com black True 299 | flashinfo.org black True 300 | flashnewscorner.com black True 301 | floridasunpost.com black True 302 | focusnews.info black True 303 | folksvideo.com black True 304 | fox-news24.com black True 305 | france.actualites.co black True 306 | freddymag.com black True 307 | freedomcrossroads.us black True 308 | freedomdaily.com black True 309 | freedomsfinalstand.com black True 310 | freshdailyreport.com black True 311 | friendsofsyria.wordpress.com black True 312 | givemeliberty01.com black True 313 | globalassociatednews.com black True 314 | globalpoliticsnow.com black True 315 | greenvillegazette.com black True 316 | guerilla.news black True 317 | guerillanews.com black True 318 | gummypost.com black True 319 | halturnershow.com black True 320 | headlinebrief.com black True 321 | healthyworldhouse.com black True 322 | heaviermetal.net black True 323 | hotglobalnews.com black True 324 | houstonchronicle-tv.com black True 325 | huzlers.com black True 326 | ilovemyfreedom.org black True 327 | interestingdailynews.com black True 328 | intrendtoday.com black True 329 | ipatriot.com black True 330 | isthatlegit.com black True 331 | jokerviral.com black True 332 | kata33.com black True 333 | klponews.com black True 334 | km8news.com black True 335 | kmt11.com black True 336 | knp7.com black True 337 | konkonsagh.biz black True 338 | krbcnews.com black True 339 | kspm33.com black True 340 | kupr7.com black True 341 | ky12news.com black True 342 | ky6news.com black True 343 | kypo6.com black True 344 | ladylibertysnews.com black True 345 | landrypost.com black True 346 | lastdeplorables.com black True 347 | liberalplug.com black True 348 | liberty-courier.com black True 349 | libertyalliance.com black True 350 | libertywritersnews.com black True 351 | local31news.com black True 352 | localnews33.com black True 353 | londonwebnews.com black True 354 | lopezreport.com black True 355 | madworldnews.com black True 356 | mainerepublicemailalert.com black True 357 | majorthoughts.com black True 358 | maywoodpost.com black True 359 | mbynews.com black True 360 | mckenziepost.com black True 361 | mediazone.news black True 362 | metropolitanworlds.com black True 363 | mississippiherald.com black True 364 | morningnewsusa.com black True 365 | mrnewswatch.com black True 366 | msfanpage.link black True 367 | msnbc.website black True 368 | nationalinsiderpolitics.com black True 369 | nationalreport.net black True 370 | nbc.com.co black True 371 | ncscooper.com black True 372 | neonnettle.com black True 373 | nephef.com black True 374 | nevo.news black True 375 | newpoliticstoday.com black True 376 | news14kgpn.com black True 377 | news14now.com black True 378 | news4ktla.com black True 379 | newsbiscuit.com black True 380 | newsbreakingspipe.com black True 381 | newsbreakshere.com black True 382 | newsbuzzdaily.com black True 383 | newsbysquad.com black True 384 | newsdaily10.com black True 385 | newsdaily12.com black True 386 | newsdaily27.com black True 387 | newsexaminer.net black True 388 | newsfeedhunter.com black True 389 | newsfeedobserver.com black True 390 | newshubs.info black True 391 | newsjustforyou1.blogspot.com black True 392 | newsleak.co black True 393 | newslo.com black True 394 | newsnow17.com black True 395 | newswatch33.com black True 396 | newzmagazine.com black True 397 | notallowedto.com black True 398 | noticias365.info black True 399 | now8news.com black True 400 | nymeta.co black True 401 | occupydemocrats.com black True 402 | onepoliticalplaza.com black True 403 | openmagazines.com black True 404 | oreillypost.com black True 405 | ourlandofthefree.com black True 406 | paris.actualites.co black True 407 | patriothangout.com black True 408 | persecutes.com black True 409 | politicops.com black True 410 | politicot.com black True 411 | politicsusanews.com black True 412 | powerdaily.us black True 413 | president45donaldtrump.com black True 414 | pressunion.org black True 415 | prntly.com black True 416 | proudleader.com black True 417 | qualitysharing.com black True 418 | react365.com black True 419 | readconservatives.news black True 420 | realnewsrightnow.com black True 421 | redcountry.us black True 422 | redinfo.us black True 423 | redrocktribune.com black True 424 | redstatewatcher.com black True 425 | religionmind.com black True 426 | rickwells.us black True 427 | rilenews.com black True 428 | rogue-nation3.com black True 429 | rumorjournal.com black True 430 | satiratribune.com black True 431 | scrapetv.com black True 432 | smhwtfnews.com black True 433 | snoopack.com black True 434 | socialeverythings.com black True 435 | southernconservativeextra.com black True 436 | spinzon.com black True 437 | statenation.co black True 438 | states-tv.com black True 439 | stgeorgegazette.com black True 440 | straightstoned.com black True 441 | stuppid.com black True 442 | success-street.com black True 443 | supremepatriot.com black True 444 | tdnewswire.com black True 445 | tdtalliance.com black True 446 | teddystick.com black True 447 | telegraphsun.com black True 448 | the-insider.co black True 449 | the-postillon.com black True 450 | theavocadonews.com black True 451 | thebostontribune.com black True 452 | thebreakingnews.co black True 453 | theexaminer.site black True 454 | thefrt.com black True 455 | theinternationalreporter.org black True 456 | theinternetpost.net black True 457 | thelastlineofdefense.org black True 458 | themoralofthestory.us black True 459 | thenationalsun.com black True 460 | thenet24h.com black True 461 | thenewsnerd.com black True 462 | thenewyorkevening.com black True 463 | thenochill.com black True 464 | thepoliticaltribune.com black True 465 | thepremiumnews.com black True 466 | theracketreport.com black True 467 | thereporterz.com black True 468 | therightists.com black True 469 | theseattletribune.com black True 470 | thetrumpmedia.com black True 471 | theusa-news.com black True 472 | theusaconservative.com black True 473 | thevalleyreport.com black True 474 | thewashingtonpress.com black True 475 | times.com.mx black True 476 | tmzbreaking.com black True 477 | tmzbusiness.com black True 478 | tmzcomedy.com black True 479 | tmzhiphop.com black True 480 | tmzuncut.com black True 481 | tmzurban.com black True 482 | tmzworldnews.com black True 483 | tmzworldstarnews.com black True 484 | trueamericans.me black True 485 | truetrumpers.com black True 486 | truthkings.com black True 487 | undergroundnewsreport.com black True 488 | unitedmediapublishing.com black True 489 | universepolitics.com black True 490 | usa-conservative.com black True 491 | usa-radio.com black True 492 | usa-television.com black True 493 | usadailyinfo.com black True 494 | usadailypost.us black True 495 | usadailytime.com black True 496 | usadosenews.com black True 497 | usafirstinformation.com black True 498 | usanews4u.us black True 499 | usanewsflash.com black True 500 | usanewshome.com black True 501 | usanewstoday.com black True 502 | usapolitics24hrs.com black True 503 | usapoliticsnow.com black True 504 | usapoliticstoday.com black True 505 | usapoliticszone.com black True 506 | usasnich.com black True 507 | usatodaynews.me black True 508 | usatodaypolitics.com black True 509 | usaworldbox.com black True 510 | ushealthyadvisor.com black True 511 | ushealthylife.com black True 512 | usherald.com black True 513 | usinfonews.com black True 514 | uspoln.com black True 515 | uspostman.com black True 516 | vesselnews.io black True 517 | viralactions.com black True 518 | viralcocaine.com black True 519 | viralcords.com black True 520 | viraldevil.com black True 521 | viralmugshot.com black True 522 | viralpropaganda.com black True 523 | viralspeech.com black True 524 | viralstuppid.com black True 525 | voxtribune.com black True 526 | washingtonevening.com black True 527 | washingtonfeed.com black True 528 | washingtonpost.com.co black True 529 | wazanews.tk black True 530 | wcpm3.com black True 531 | weconservative.com black True 532 | weekendherald.com black True 533 | wetheproudpatriots.com black True 534 | wftj8news.com black True 535 | whatsupic.com black True 536 | witscience.org black True 537 | wleb21.com black True 538 | wm21news.com black True 539 | wmacnews.com black True 540 | wmb36.com black True 541 | world-politicus.com black True 542 | worldinformation24.info black True 543 | worldnewsdailyreport.com black True 544 | worldnewspolitics.com black True 545 | worldpoliticsnow.com black True 546 | worldpoliticus.com black True 547 | wrejnews.com black True 548 | wrpt16.com black True 549 | wtoe5news.com black True 550 | xbn-news.com black True 551 | yesimright.com black True 552 | yournewswire.com black True 553 | zootfeed.com black True 554 | -------------------------------------------------------------------------------- /replicate.sh: -------------------------------------------------------------------------------- 1 | # Replication script for generating web domains table 2 | 3 | # Download and unzip external data sources 4 | cd data 5 | URL_BIAS='http://personalization.ccs.neu.edu/static/archive/bias_scores.tar.gz' 6 | curl -o bias_scores.tar.gz $URL_BIAS 7 | tar -xzvf bias_scores.tar.gz 8 | rm bias_scores.tar.gz 9 | 10 | URL_FAKE='https://github.com/LazerLab/twitter-fake-news-replication/trunk/domains/domain_coding' 11 | svn export $URL_FAKE 12 | cd - 13 | 14 | # Install virtual environment and pkgs for csv and excel data 15 | virtualenv venv --python=python3.6 16 | source venv/bin/activate 17 | pip install pandas xlrd 18 | 19 | python code/fake_news.py 20 | # Extract fake news data 21 | # in: 22 | # data/domain_coding/data/black_sites.txt 23 | # data/domain_coding/data/Domain Codings.xlsx 24 | # out: 25 | # data/fake_news.tsv 26 | 27 | python code/aggregate_domains.py 28 | # Merge all, keyed by domain 29 | # in: 30 | # data/fake_news.tsv 31 | # data/bias_scores/bias_scores.csv 32 | # out: 33 | # data/domains/domains.tsv 34 | 35 | deactivate --------------------------------------------------------------------------------