Tweeting the terror: modelling the social media reaction to the Woolwich terrorist attack
Tóm tắt
Little is currently known about the factors that promote the propagation of information in online social networks following terrorist events. In this paper we took the case of the terrorist event in Woolwich, London in 2013 and built models to predict information flow size and survival using data derived from the popular social networking site Twitter. We define information flows as the propagation over time of information posted to Twitter via the action of retweeting. Following a comparison with different predictive methods, and due to the distribution exhibited by our dependent size measure, we used the zero-truncated negative binomial (ZTNB) regression method. To model survival, the Cox regression technique was used because it estimates proportional hazard rates for independent measures. Following a principal component analysis to reduce the dimensionality of the data, social, temporal and content factors of the tweet were used as predictors in both models. Given the likely emotive reaction caused by the event, we emphasize the influence of emotive content on propagation in the discussion section. From a sample of Twitter data collected following the event (N = 427,330) we report novel findings that identify that the sentiment expressed in the tweet is statistically significantly predictive of both size and survival of information flows of this nature. Furthermore, the number of offline press reports relating to the event published on the day the tweet was posted was a significant predictor of size, as was the tension expressed in a tweet in relation to survival. Furthermore, time lags between retweets and the co-occurrence of URLS and hashtags also emerged as significant.
Từ khóa
Tài liệu tham khảo
Backstrom L, Kleinberg J, Lee L, Danescu-Niculescu-Mizil C (2013) Characterizing and curating conversation threads: expansion, focus, volume, re-entry. Paper presented at the proceedings of the sixth ACM international conference on web search and data mining, Rome, Italy
Bandari R, Asur S, Huberman BA (2012) The pulse of news in social media: forecasting popularity. CoRR. http://arxiv.org/abs/1202.0332
Berger J, Milkman K (2012) What makes online content viral? J Mark Res 49(2):192–205
Burnap P, Rana O, Avis N, Williams M, Housley W, Edwards A, Morgan J, S L (2013) Detecting tension in online communities with computational Twitter analysis. Technol Forecast Social Change. doi:10.1016/j.techfore.2013.04.013
Cox D (1972) Regression models and life tables. J Roy Statist Soc B 34:187–220
Downs A (1972) Up and down with ecology––the ‘issue-attention cycle’. Public Interest 28:28–50
Guille A, Hacid H (2012) A predictive model for the temporal dynamics of information diffusion in online social networks. Paper presented at the 21st international conference companion on World Wide Web, Lyon, France
Guille A, Hacid H, Favre C, Zighed DA (2013) Information diffusion in online social networks: a survey. SIGMOD Rec 42(1):17–28. doi:10.1145/2503792.2503797
Lin Y, Margolin D, Keegan B, Baronchelli A, Lazer D (2013) #Bigbirds never die: understanding social dynamics of emergent hashtags. In: Proceedings of the seventh international AAAI conference on weblogs and social media, Boston, MA
Lotan G, Graeff E, Ananny M, Gaffney D, Pearce I, Boyd D (2011) The revolutions were tweeted: information flows during the 2011 Tunisian and Egyptian revolutions. Int J Commun 5(Special Issue):1375–1405
Macskassy S, Michelson M (2011) Why do people retweet? antihomophily wins the day. In: International conference on weblogs and social media (ICWSM)
Procter R, Crump J, Karstedt S, Voss A, Cantijoch M (2013a) Reading the riots: what were the police doing on Twitter? Polic Soc 23(4):1–24. doi:10.1080/10439463.2013.780223
Procter R, Vis F, Voss A (2013b) Reading the riots on Twitter: methodological innovation for the analysis of big data. Int J Soc Res Methodol 16(3):197–214. doi:10.1080/13645579.2013.774172
Suh B, Hong L, Pirolli P, Chi E (2011) Want to be retweeted? Large scale analytics on factors impacting retweet in Twitter network. In: SocialCom
Tabachnick B, Fidell L (2013) Using multivariate statistics, 6th edn. Allyn and Bacon, Boston
Thelwall M, Buckley K, Paltogou G, Cai D, Kappas A (2010) Sentiment strength detection in short informal text. J Am Soc Inform Sci Technol 61(12):25442558
Tsur O, Rappoport A (2012) What’s in a hashtag?: content based prediction of the spread of ideas in microblogging communities. Paper presented at the proceedings of the fifth ACM international conference on web search and data mining, Seattle, Washington, USA
Williams ML, Edwards A, Housley W, Burnap P, Rana O, Avis N, Morgan J, Sloan L (2013) Policing cyber-neighbourhoods: tension monitoring and social media networks. Polic Soc 23(4):1–21. doi:10.1080/10439463.2013.780225
Yang J, Counts S (2010) Predicting the speed, scale, and rangeof information diffusion in Twitter. In: International conference on weblogs and social media (ICWSM)
Zaman T, Herbrich R, Van Gael J, Stern D (2010) Predicting information spreading in Twitter. In: Workshop on computational social science and the wisdom of crowds (NIPS). http://arxiv.org/abs/1304.6777
Zaman T, Fox E, Bradlow E (2013) A Bayesian approach for predicting the popularity of tweets. CoRR
Zarrella D (2009) The science of retweets