Abstract
In this paper, we are interested in understanding the interrelationships between mainstream and social media in forming public opinion during mass crises, specifically in regards to how events are framed in the mainstream news and on social networks and to how the language used in those frames may allow to infer political slant and partisanship. We study the lingual choices for political agenda setting in mainstream and social media by analyzing a dataset of more than 40M tweets and more than 4M news articles from the mass protests in Ukraine during 2013–2014—known as “Euromaidan”—and the post-Euromaidan conflict between Russian, pro-Russian and Ukrainian forces in eastern Ukraine and Crimea. We design a natural language processing algorithm to analyze at scale the linguistic markers which point to a particular political leaning in online media and show that political slant in news articles and Twitter posts can be inferred with a high level of accuracy. These findings allow us to better understand the dynamics of partisan opinion formation during mass crises and the interplay between mainstream and social media in such circumstances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We used the Skip-Gram model as it provided more interpretable results.
- 2.
Gensim natural language processing library https://radimrehurek.com/gensim/.
- 3.
as ranked by the Medialogia rating agency http://goo.gl/JNvx0Y.
- 4.
This is achieved through filtering the corpora by the relevant keywords, i.e., “kyiv”, “ukraine”, “donbass”, “maidan”, “crimea”, “luhansk”, “dnr” and “lnr”. Adding a wider set of keywords had little effect on improving the recall of filtering.
- 5.
We refer to each of these three classes as ‘party’ or ‘parties’ in the rest of this paper.
- 6.
Note that this is equivalent to using the mean \(\frac{\sum _{s \in S}{\rho _w^s}}{|S|}\), since the sum for all words is computed over the same set of sources S.
- 7.
We note that a straightforward approach of removing the most prominent news source markers – as measured by the relative frequency introduced in the previous section – has proved to be inefficient for the considered classification problem. In contrast, the method we introduce in the rest of this section provides a more nuanced approach in estimating the relevance of each classification feature.
- 8.
The proposed approach was implemented by adapting the internal implementation of the Random Forest algorithm from the open source scikit-learn libary.
References
An, J., Cha, M., Gummadi, K.P., Crowcroft, J., Quercia, D.: Visualizing media bias through Twitter. In: Sixth International AAAI Conference on Weblogs and Social Media (2012)
An, J., Cha, M., Gummadi, P.K., Crowcroft, J.: Media landscape in Twitter: a world of new conventions and political diversity. In: ICWSM (2011)
An, J., Quercia, D., Cha, M., Gummadi, K., Crowcroft, J.: Sharing political news: the balancing act of intimacy and socialization in selective exposure. EPJ Data Sci. 3(1), 1–21 (2014)
An, J., Quercia, D., Crowcroft, J.: Fragmented social media: a look into selective exposure to political news. In: Proceedings of World Wide Web Companion (2013)
An, J., Quercia, D., Crowcroft, J.: Partisan sharing: Facebook evidence and societal consequences. In: Proceedings of ACM COSN (2014)
Aragón, P., Volkovich, Y., Laniado, D., Kaltenbrunner, A.: When a movement becomes a party: computational assessment of new forms of political organization in social media. In: Tenth International AAAI Conference on Web and Social Media (2016)
Boutet, A., Kim, H., Yoneki, E.: What’s in Twitter, I know what parties are popular and who you are supporting now! Soc. Netw. Anal. Min. 3(4), 1379–1391 (2013)
Brodersen, A., Scellato, S., Wattenhofer, M.: Youtube around the world: geographic popularity of videos. In: Proceedings of WWW (2012)
Chakraborty, A., Ghosh, S., Ganguly, N., Gummadi, K.P.: Dissemination biases of social media channels: on the topical coverage of socially shared news. In: Tenth International AAAI Conference on Web and Social Media (2016)
Cohen, R., Ruths, D.: Classifying political orientation on Twitter: it’s not easy! In: ICWSM (2013)
Conover, M.D., Gonçalves, B., Ratkiewicz, J., Flammini, A., Menczer, F.: Predicting the political alignment of Twitter users. In: 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third Inernational Conference on Social Computing (SocialCom), pp. 192–199. IEEE (2011)
Diuk, N.: Euromaidan: Ukraine’s self-organizing revolution. World Affairs 176(6), 9–16 (2014)
Goldstein, J.: The role of digital networked technologies in the Ukrainian orange revolution. Berkman Center Research Publication (2007)
González-Bailón, S., Borge-Holthoefer, J., Moreno, Y.: Broadcasters and hidden influentials in online protest diffusion. Am. Behav. Sci. (2013)
González-Bailón, S., et al.: The dynamics of protest recruitment through an online network. Sci. Rep. 1 (2011)
Hegelich, S., Janetzko, D.: Are social bots on twitter political actors? Empirical evidence from a Ukrainian social botnet. In: Tenth International AAAI Conference on Web and Social Media (2016)
Howard, P.N.: The Digital Origins of Dictatorship and Democracy. Information Technology and Political Islam. Oxford University Press, Oxford (2010)
Mikolov, T., et al.: Distributed representations of words and phrases and their compositionality. In: NIPS (2013)
Mikolov, T., et al.: Efficient estimation of word representations in vector space. In: Proceedings of Workshop at ICLR (2013)
Oates, S., Lokot, T.: Twilight of the gods?: How the Internet challenged Russian television news frames in the winter protests of 2011–2012. In: International Association for Media and Communication Research Annual Conference (2013)
Onuch, O.: Euromaidan protests in Ukraine: social media versus social networks. Probl. Post-Communism 62, 1–19 (2015)
Papacharissi, Z., Chadwick, A.: The virtual sphere 2.0: the internet, the public sphere, and beyond. In: Routledge Handbook of Internet Politics, pp. 230–245 (2009)
Pennacchiotti, M., Popescu, A.M.: Democrats, republicans and starbucks afficionados: user classification in twitter. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 430–438. ACM (2011)
Pennacchiotti, M., Popescu, A.M.: A machine learning approach to Twitter user classification. In: ICWSM 2011, vol. 1, pp. 281–288 (2011)
Szostek, J.: The media battles of Ukraine’s Euromaidan. Digital Icons 11, 1–19 (2014)
Vijayaraghavan, P., Vosoughi, S., Roy, D.: Automatic detection and categorization of election-related tweets. arXiv preprint arXiv:1605.05150 (2016)
Zelinska, O.: Who were the protestors and what did they want? Demokratizatsiya 23(4), 379–400 (2015)
Zeng, L., Starbird, K., Spiro, E.S.: # unconfirmed: classifying rumor stance in crisis-related social media messages. In: Tenth International AAAI Conference on Web and Social Media (2016)
Zhukov, Y.M., Baum, M.A.: Reporting bias and information warfare. In: International Studies Association Annual Convention (2016)
Acknowledgements
This work was supported by the Space for Sharing (S4S) project (Grant No. ES/M00354X/1). We would also like to thank the developers of the Kobzi application for providing the News-UA dataset.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Karamshuk, D., Lokot, T., Pryymak, O., Sastry, N. (2016). Identifying Partisan Slant in News Articles and Twitter During Political Crises. In: Spiro, E., Ahn, YY. (eds) Social Informatics. SocInfo 2016. Lecture Notes in Computer Science(), vol 10046. Springer, Cham. https://doi.org/10.1007/978-3-319-47880-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-47880-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-47879-1
Online ISBN: 978-3-319-47880-7
eBook Packages: Computer ScienceComputer Science (R0)