ABSTRACT
Using a novel methodological approach to measure emotions in Facebook comments, this Work in Progress (WIP) paper explores the relationship between negative feelings and ideological cross-posting behavior. Using the VoxPopuli data harvester, we collect over 770,000 public Facebook comments1 from the three major political campaign pages active during the Brexit referendum. After sorting users into ideological camps based on their reactions to campaign posts, we then examine their commenting patterns across ideological lines. Using three different methods of sentiment analysis, we identify negative and positive emotions and their fine-grained sub-categories in comments. The analysis reveals one quarter of all comments are cross-ideological posts, with Leave supporters overwhelmingly active in commenting on Remain posts. A comparison across the campaigns shows that Brexiteers are much more likely to express anger than Remainers.
- Zizi Papacharissi. 2015. Affective Publics: Sentiment, Technology, and Politics. Oxford, Oxford University Press.Google Scholar
- Cass Sunstein. 2017. #Republic: Divided Democracy in the Age of Social Media. Princeton, Princeton University Press.Google Scholar
- Eytan Bakshy, Solomon Messing, and Lada Adamic. (2015). Exposure to ideologically diverse news and opinion on Facebook. Science 348, 6239 (June 2015), 1130--1132.Google ScholarCross Ref
- Anatoliy Gruzd and Jeffrey Roy. 2014. Investigating Political Polarization on Twitter: A Canadian perspective. Policy & Internet 6, 1 (March 2014), 28--45.Google ScholarCross Ref
- David Ost. 2004. Politics as the Mobilization of Anger: Emotions in Movements and in Power. European Journal of Social Theory 7, 2 (May 2014), 229--244.Google ScholarCross Ref
- Jeff Goodwin, James M. Jasper, and Francesca Polletta (Eds.). 2009. Passionate Politics: Emotions and Social Movements. Chicago: University of Chicago Press.Google Scholar
- Homero Gil de Zúñiga, Logan Molyneux, and Pei Zheng. 2014. Social Media, Political Expression, and Political Participation. Journal of Communication 64, 4 (August 2014), 612--634.Google Scholar
- Anamaria Dutceac Segesten and Michael Bossetta. 2017. A Typology of Political Participation Online: How Citizens used Twitter to Mobilize During the 2015 British General Elections. Information, Communication & Society 20, 11 (March 2017). 1625--1643.Google ScholarCross Ref
- Zeynep Tufekci. 2014. Big Questions for Social Media Big Data: Representativeness, Validity and Other Methodological Pitfalls. In Proceedings of the Eighth Int'l AAAI Conference on Weblogs and Social Media (ICWSM '14), Ann Arbor, MI, 505--514.Google Scholar
- Stefan Stieglitz and Linh Dang-Xuan. 2012. Political Communication and influence through Microblogging: An Empirical Analysis of Sentiment in Twitter Messages and Retweet Behavior. In Proceeding of the 45th Hawaii Int'l Conf. on System Science, Maui, 3500--3509. Google ScholarDigital Library
- Yunya Song, Xin-Yu Dai, and Jia Wang. 2016. Not all Emotions are Created Equal: Expressive Behavior of the Networked Public on China's Social Media Site. Computers in Human Behavior 60 (July 2016), 525--533. Google ScholarDigital Library
- Jonah Berger and Katherine L. Milkman. 2012. What makes Online Content Viral?. Journal of Marketing Research 49, 2 (April 2012), 192--205.Google ScholarCross Ref
- James Russel. 1980. A Circumplex Model of Affect. Journal of Personality and Social Psychology 39, 6 (December1980): 1161--1178.Google Scholar
- Chris Zimmerman, Mari-Klara Stein, Daniel Hardt, Christian Danielsen, and Ravi Vatrapu. 2016. emotionVis: Designing an Emotion Text Inference Tool for Visual Analytics. In Int'l Conf. on Design Science Research in Information Systems, Canada, 238--244. Google ScholarDigital Library
- Sherlock Campbell and James W. Pennebaker. 2003. "The Secret Life of Pronouns: Flexibility in Writing Style and Physical Health. Psychological science 14, 1 (January 2003), 60--65.Google Scholar
- Stefan Deborteli, Oliver Müller, Iris A. Junglas, and Jan vom Brocke. 2016. Text Mining for Information Systems Researchers: An Annotated Topic Modeling Tutorial. Communications of the Association for Information Systems 39 (July 2016), 111--135.Google Scholar
Index Terms
- Shouting at the Wall: Does Negativity Drive Ideological Cross-posting in Brexit Facebook Comments?
Recommendations
'The good old days'
Humans are reflective, adaptive, and social. They recall the past, sometimes discuss these recollections with others and become nostalgic; yet, previous research has not examined nostalgia in social media. This paper investigates the expression of ...
Sentiment, emotion, purpose, and style in electoral tweets
We automatically compile a dataset of 2012 US presidential election tweets.We annotate the tweets for sentiment, emotion, style, and purpose.We show that the tweets convey negative emotions twice as often as positive.We describe two automatic systems ...
MAS: A Corpus of Tweets for Marketing in Spanish
The Semantic Web: ESWC 2018 Satellite EventsAbstractThis paper presents a corpus of tweets in Spanish language which were manually tagged for marketing purposes. The used tags describe three aspects of the text of each Twitter post. First, the emotions a brand caused to the author from among a ...
Comments