ABSTRACT
This paper investigates bias in coverage between Western and Arab media on Twitter after the November 2015 Beirut and Paris terror attacks. Using two Twitter datasets covering each attack, we investigate how Western and Arab media differed in coverage bias, sympathy bias, and resulting information propagation. We crowdsourced sympathy and sentiment labels for 2,390 tweets across four languages (English, Arabic, French, German), built a regression model to characterize sympathy, and thereafter trained a deep convolutional neural network to predict sympathy. Key findings show: (a) both events were disproportionately covered (b) Western media exhibited less sympathy, where each media coverage was more sympathetic towards the country affected in their respective region (c) Sympathy predictions supported ground truth analysis that Western media was less sympathetic than Arab media (d) Sympathetic tweets do not spread any further. We discuss our results in light of global news flow, Twitter affordances, and public perception impact.
Supplemental Material
Available for Download
A.chi2018_dataset.csv: Our final annotated, multi-language (English, Arabic, French, German) dataset (N=2,390). B.chi2018_news_queries.pdf: Contains a table that shows: (1) full set of queries (in English and native language) used to crawl Twitter user accounts (2) the total number of Twitter news accounts found (3) the amount and percentage found in each dataset (Beirut, Paris). C.chi2018_news_org_summary.csv: The final list of unique crawled news organizations (N=208). For ethical concerns, we only show the name, user name, the country / query used to retrieve the account, the follower count at the time of crawling, the number of tweets, and our mean and standard deviation scores of crowdsourced labels. D.chi2018_cf_instructions.pdf: Crowdsourcing annotation task instructions given to crowdworkers. Translated from English by native (bilingual) speakers into French, Arabic, and German. README.md
- Sofiane Abbar, Jisun An, Haewoon Kwak, Yacine Messaoui, and Javier Borge-Holthoefer. 2015. Consumers and Suppliers: Attention asymmetries. A Case Study of Aljazeera's News Coverage and Comments. In Computation+Journalism Symposium 2015. http://cj2015.brown.columbia.edu/papers/ consumers-and-suppliers.pdfGoogle Scholar
- Jisun An, Haewoon Kwak, Yelena Mejova, Sonia Alonso Saenz De Oger, and Braulio Gomez Fortes. 2016. Are You Charlie or Ahmed? Cultural Pluralism in Charlie Hebdo Response on Twitter. In Proc. ICWSM '16. 2--11. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM16/paper/ view/12997Google Scholar
- David P. Baron. 2006. Persistent media bias. Journal of Public Economics 90, 1--2 (January 2006), 1--36. https: //ideas.repec.org/a/eee/pubec/v90y2006i1--2p1--36.htmlGoogle ScholarCross Ref
- Jonah Berger and Katherine L. Milkman. 2012. What Makes Online Content Viral? Journal of Marketing Research 49, 2 (2012), 192--205.Google ScholarCross Ref
- Shane Bergsma, Paul McNamee, Mossaab Bagdouri, Clayton Fink, and Theresa Wilson. 2012. Language identification for creating language-specific twitter collections. In Proc. LSM '12. ACL, 65--74. Google ScholarDigital Library
- Javier Borge-Holthoefer, Walid Magdy, Kareem Darwish, and Ingmar Weber. 2015. Content and Network Dynamics Behind Egyptian Political Polarization on Twitter. In Proc. CSCW '15. ACM Press, 700--711. Google ScholarDigital Library
- D. Britz. 2015. Implementing a CNN for Text Classification in Tensorflow. (2015). https://github.com/dennybritz/cnn-text-classification-tfGoogle Scholar
- Meeyoung Cha, Hamed Haddadi, Fabrício Benevenuto, and Krishna P. Gummadi. 2010. Measuring user influence in Twitter: The million follower fallacy. In Proc. ICWSM '10. http://twitter.mpi-sws.org/icwsm2010_fallacy.pdfGoogle Scholar
- D D'Alessio and M Allen. 2000. Media bias in presidential elections: a meta-analysis. Journal of Comm. 50, 4 (2000), 133--156.Google ScholarCross Ref
- Alexander Dallmann, Florian Lemmerich, Daniel Zoller, and Andreas Hotho. 2015. Media Bias in German Online Newspapers. In Proc. HT '15. ACM, New York, NY, USA, 133--137. Google ScholarDigital Library
- Jean Decety and Thierry Chaminade. 2003. Neural correlates of feeling sympathy. Neuropsychologia 41, 2 (2003), 127--138. The cognitive neuroscience of social behavior.Google ScholarCross Ref
- Mark Deuze. 2002. National news cultures: A comparison of Dutch, German, British, Australian, and US journalists. Journalism&Mass Communication Quarterly 79, 1 (2002), 134--149.Google ScholarCross Ref
- Nicholas Diakopoulos, Munmun De Choudhury, and Mor Naaman. 2012. Finding and Assessing Social Media Information Sources in the Context of Journalism. In Proc. CHI '12. ACM, 2451--2460. Google ScholarDigital Library
- Nicholas Diakopoulos and Arkaitz Zubiaga. 2014. Newsworthiness and Network Gatekeeping on Twitter: The Role of Social Deviance.. In ICWSM '14. AAAI. http://www.aaai.org/ocs/index.php/ICWSM/ICWSM14/paper/view/8065Google Scholar
- Nicholas A. Diakopoulos and David A. Shamma. 2010. Characterizing Debate Performance via Aggregated Twitter Sentiment. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '10). ACM, New York, NY, USA, 1195--1198. Google ScholarDigital Library
- Júlio Cesar dos Reis, Fabrício Benevenuto, Pedro Olmo S. Vaz de Melo, Raquel O. Prates, Haewoon Kwak, and Jisun An. 2015. Breaking the News: First Impressions Matter on Online News., In Proc. ICWSM '15. CoRR (2015). http://arxiv.org/abs/1503.07921Google Scholar
- R.A. Fisher. 1925. Statistical methods for research workers. Edinburgh Oliver&Boyd.Google Scholar
- Johan Galtung and Mari Holmboe Ruge. 1965. The Structure of Foreign News: The Presentation of the Congo, Cuba and Cyprus Crises in Four Norwegian Newspapers. Journal of Peace Research 2, 1 (1965), 64--90.Google ScholarCross Ref
- C.J. Glynn, S. Herbst, G.J. O'Keefe, and R.Y. Shapiro. 2004. Public Opinion. Westview Press. https://books.google.de/books?id=b3OqBAAAQBAJGoogle Scholar
- Jennifer Golbeck and Derek Hansen. 2011. Computing Political Preference Among Twitter Followers. In Proc. CHI '11. ACM, 1105--1108. Google ScholarDigital Library
- Yoav Goldberg. 2015. A Primer on Neural Network Models for Natural Language Processing. CoRR abs/1510.00726 (2015). http://arxiv.org/abs/1510.00726Google Scholar
- Sandra González-Bailón, Ning Wang, Alejandro Rivero, Javier Borge-Holthoefer, and Yamir Moreno. 2014. Assessing the bias in samples of large online networks. Soc. Net. 38 (2014), 16--27.Google ScholarCross Ref
- Thomas Hanitzsch, Folker Hanusch, Claudia Mellado, Maria Anikina, Rosa Berganza, Incilay Cangoz, Mihai Coman, Basyouni Hamada, María Elena Hernández, Christopher D Karadjov, and others. 2011. Mapping journalism cultures across nations: A comparative study of 18 countries. Journalism Studies 12, 3 (2011), 273--293.Google ScholarCross Ref
- Lars Kai Hansen, Adam Arvidsson, Finn Aarup Nielsen, Elanor Colleoni, and Michael Etter. 2011. Good Friends, Bad News - Affect and Virality in Twitter. Springer Berlin Heidelberg, 34--43.Google Scholar
- E.S. Herman and N. Chomsky. 1988. Manufacturing consent: the political economy of the mass media. Pantheon Books. https://books.google.de/books?id=Up5sAAAAIAAJGoogle Scholar
- Isaac Johnson, Connor McMahon, Johannes Schöning, and Brent Hecht. 2017. The Effect of Population and "Structural" Biases on Social Media-based Algorithms: A Case Study in Geolocation Inference Across the Urban-Rural Spectrum. In Proc. CHI '17. ACM, 1167--1178. Google ScholarDigital Library
- Isaac L. Johnson, Subhasree Sengupta, Johannes Schöning, and Brent Hecht. 2016. The Geography and Importance of Localness in Geotagged Social Media. In Proc. CHI '16. ACM, 515--526. Google ScholarDigital Library
- Ankit Kariryaa, Isaac Johnson, Brent Hecht, and Johannes Schöning. 2018. Defining and Predicting the Localness of Volunteered Geographic Information using Ground Truth Data. In Proc. CHI '18. ACM. Google ScholarDigital Library
- Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. In Proc. EMNLP '14, Alessandro Moschitti, Bo Pang, and Walter Daelemans (Eds.). ACL, 1746--1751. http://aclweb.org/anthology/D/D14/D14--1181.pdfGoogle ScholarCross Ref
- Yonghwan Kim, Youngju Kim, Joong Suk Lee, Jeyoung Oh, and Na Yeon Lee. 2015. Tweeting the public: journalists' Twitter use, attitudes toward the public's tweets, and the relationship with the public. Information, Communication&Society 18, 4 (2015), 443--458.Google Scholar
- James T Kost and Michael P McDermott. 2002. Combining dependent P-values. Statistics&Probability Letters 60, 2 (2002), 183--190.Google ScholarCross Ref
- Haewoon Kwak and Jisun An. 2014a. SocInfo. Springer, Chapter A First Look at Global News Coverage of Disasters by Using the GDELT Dataset, 300--308.Google Scholar
- Haewoon Kwak and Jisun An. 2014b. Understanding News Geography and Major Determinants of Global News Coverage of Disasters. CoRR abs/1410.3710 (2014). http://arxiv.org/abs/1410.3710Google Scholar
- V. I. Levenshtein. 1966. Binary codes capable of correcting deletions, insertions and reversals. Soviet Phys. Doklady. 10, 8 (Feb. 1966), 707--710.Google Scholar
- Lin, Yu-Ru and Margolin, Drew. 2014. The ripple of fear, sympathy and solidarity during the Boston bombings. EPJ Data Sci. 3, 1 (2014), 31.Google ScholarCross Ref
- Gilad Lotan, Erhardt Graeff, Mike Ananny, Devin Gaffney, Ian Pearce, and danah boyd. 2011. The Arab Spring| The Revolutions Were Tweeted: Information Flows during the 2011 Tunisian and Egyptian Revolutions. International Journal of Communication 5, 0 (2011). http://ijoc.org/index.php/ijoc/article/view/1246Google Scholar
- Marco Lui and Timothy Baldwin. 2012. Langid.Py: An Off-the-shelf Language Identification Tool. In Proc. ACL '12 System Demonstrations. ACL, Stroudsburg, PA, USA, 25--30. http://dl.acm.org/citation.cfm?id=2390470.2390475 Google ScholarDigital Library
- Walid Magdy, Kareem Darwish, Norah Abokhodair, Afshin Rahimi, and Timothy Baldwin. 2016. #ISISisNotIslam or #DeportAllMuslims?: Predicting Unspoken Views. In Proc. WebSci '16. ACM, New York, NY, USA, 95--106. Google ScholarDigital Library
- Winter Mason and Siddharth Suri. 2012. Conducting behavioral research on Amazon's Mechanical Turk. Behavior Research Methods 44, 1 (2012), 1--23.Google ScholarCross Ref
- Yelena Mejova, Amy X. Zhang, Nicholas Diakopoulos, and Carlos Castillo. 2014. Controversy and sentiment in online news. Symposium on Computation and Journalism (2014). https://arxiv.org/abs/1409.8152Google Scholar
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. ICLR (2013). https://arxiv.org/abs/1301.3781Google Scholar
- Soo Jung Moon and Patrick Hadley. 2014. Routinizing a New Technology in the Newsroom: Twitter as a News Source in Mainstream Media. Journal of Broadcasting&Electronic Media 58, 2 (2014), 289--305.Google ScholarCross Ref
- Jonathan Scott Morgan, Cliff Lampe, and Muhammad Zubair Shafiq. 2013. Is News Sharing on Twitter Ideologically Biased?. In Proc. CSCW '13. ACM, New York, NY, USA, 887--896. Google ScholarDigital Library
- Alexandra Olteanu, Sarah Vieweg, and Carlos Castillo. 2015. What to Expect When the Unexpected Happens: Social Media Communications Across Crises. In Proc. CSCW '15. ACM, New York, NY, USA, 994--1009. Google ScholarDigital Library
- Bo Pang and Lillian Lee. 2008. Opinion Mining and Sentiment Analysis. Found. Trends Inf. Retr. 2, 1--2 (Jan. 2008), 1--135. Google ScholarDigital Library
- Souneil Park, Seungwoo Kang, Sangyoung Chung, and Junehwa Song. 2009. NewsCube: Delivering Multiple Aspects of News to Mitigate Media Bias. In Proc. CHI '09. ACM, New York, NY, USA, 443--452. Google ScholarDigital Library
- Richard M. Perloff. 2015. A Three-Decade Retrospective on the Hostile Media Effect. Mass Communication and Society 18, 6 (2015), 701--729.Google ScholarCross Ref
- Vincent Price and David Tewksbury. 1997. News values and public opinion: A theoretical account of media priming and framing. Progress in communication sciences (1997), 173--212.Google Scholar
- Diego Saez-Trumper, Carlos Castillo, and Mounia Lalmas. 2013. Social media news communities: gatekeeping, coverage, and statement bias. In Proc. CIKM '13. ACM, 1679--1684. Google ScholarDigital Library
- Axel Schulz, T Thanh, H Paulheim, and Immanuel Schweizer. 2013. A fine-grained sentiment analysis approach for detecting crisis related microposts. ISCRAM 2013 (2013). http://idl.iscram.org/files/schulz/2013/ 927_Schulz_etal2013.pdfGoogle Scholar
- Elad Segev. 2015. Visible and invisible countries: News flow theory revised. Journalism 16, 3 (2015), 412--428.Google ScholarCross Ref
- David A. Shamma, Lyndon Kennedy, and Elizabeth F. Churchill. 2009. Tweet the Debates: Understanding Community Annotation of Uncollected Sources. In Proc. WSM '09. ACM, New York, NY, USA, 3--10. Google ScholarDigital Library
- P.J. Shoemaker and S.D. Reese. 1996. Mediating the Message: Theories of Influences on Mass Media Content. Longman. https://books.google.de/books?id=E_HtAAAAMAAJGoogle Scholar
- J. Singer. 2006. Journalists and News Bloggers: Complements, Contradictions and Challenges. In Uses of Blogs, A. Bruns and J. Jacobs (Eds.). Peter Lang, New York, 23--32. http://openaccess.city.ac.uk/4024/Google Scholar
- Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research 15 (2014), 1929--1958. http://jmlr.org/papers/v15/srivastava14a.html Google ScholarDigital Library
- Kate Starbird and Leysia Palen. 2012. (How) will the revolution be retweeted?: information diffusion and the 2011 Egyptian uprising. In Proc. CSCW '12. ACM, 7--16. http://dl.acm.org/citation.cfm?id=2145212 Google ScholarDigital Library
- Saúl Vargas, Richard Mccreadie, Craig Macdonald, and Iadh Ounis. 2016. Comparing Overall and Targeted Sentiments in Social Media during Crises. In Proc. ICWSM '16. https://www.aaai.org/ocs/index.php/ICWSM/ ICWSM16/paper/view/13066Google Scholar
- Wayne Wanta, Guy Golan, and Cheolhan Lee. 2004. Agenda Setting and International News: Media Influence on Public Perceptions of Foreign Nations. Journalism&Mass Communication Quarterly 81, 2 (2004), 364--377.Google ScholarCross Ref
- Zhongyu Wei, Yulan He, Wei Gao, Binyang Li, Lanjun Zhou, and Kam-fai Wong. 2013. Mainstream Media Behavior Analysis on Twitter: A Case Study on UK General Election. In Proc. HT '13. ACM, 174--178. Google ScholarDigital Library
- HD Wu. 2000. Systemic determinants of international news coverage: a comparison of 38 countries. Journal of Comm. 50, 2 (2000), 110--130.Google ScholarCross Ref
- Sevgi Yigit-Sert, Ismail Sengor Altingovde, and Özgür Ulusoy. 2016. Towards Detecting Media Bias by Utilizing User Comments. In Proc. WebSci '16. ACM, New York, NY, USA, 374--375. Google ScholarDigital Library
- Arjumand Younus, Muhammad Atif Qureshi, Suneel Kumar Kingrani, Muhammad Saeed, Nasir Touheed, Colm O'Riordan, and Pasi Gabriella. 2012. Investigating Bias in Traditional Media Through Social Media. In Proc. WWW '12 Companion. ACM, New York, NY, USA, 643--644. Google ScholarDigital Library
- Matthew D. Zeiler. 2012. ADADELTA: An Adaptive Learning Rate Method. CoRR abs/1212.5701 (2012). http://arxiv.org/abs/1212.5701Google Scholar
Index Terms
- Measuring, Understanding, and Classifying News Media Sympathy on Twitter after Crisis Events
Recommendations
Breaking news on twitter
CHI '12: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsAfter the news of Osama Bin Laden's death leaked through Twitter, many people wondered if Twitter would fundamentally change the way we produce, spread, and consume news. In this paper we provide an in-depth analysis of how the news broke and spread on ...
What is Twitter, a social network or a news media?
WWW '10: Proceedings of the 19th international conference on World wide webTwitter, a microblogging service less than three years old, commands more than 41 million users as of July 2009 and is growing fast. Twitter users tweet about any topic within the 140-character limit and follow others to receive their tweets. The goal ...
Media Mediate Sentiments: Exploratory Analysis of Tweets Posted Before, During, and After the Great East Japan Earthquake
When the Great East Japan Earthquake occurred, Twitter was used as an infrastructure for sharing information carried by other media. In other words, Twitter is considered as a "meta medium." Earthquake-related tweets included information that was of ...
Comments