Happiness travels quickly in comparison to sadness or disgust, but proliferation of anger and fear surpasses them all. This defines the bottom-line of information virality on social media. Pertinent psychological studies convey that human emotions may be ‘activated’ or ‘deactivated’ to drive people to take action. Based on this, we propose the use of cognitive behavioural features to assess the virality of information in tweets by finding a dominant emotion of same type across tweets as an indicator of viral spread. Fluctuations in emotions convey uncertainty and may reduce the frequency and intensity of discussion of a trending topic. The proposed virality prediction framework detects the emotion quotient (EQ), a measure of emotional intensity associated with five emotions, namely, fear, disgust, sadness, anger, and happiness for the exposed information in tweets to predict its outburst, i.e., virality, pertaining to social and political issues. The hybrid (lexicon + supervised learning) approach using parts-of-speech (adjectives, adverbs, verbs, emoticons) is proffered to transform the tweet into an emotional vector representative of the sentimental value for a trending topic. This emotional quantifier is then used as an empirical evidence to determine the likelihood of information going viral based on the strength of emotion in tweets and its no. of re-tweets. Preliminary results clearly demonstrate the effectiveness of the approach which affirms information virality.

Viral, Twitter, Emotion

[1]. Social Media Statistics: http://www.statista.com
[2]. Twitter: http://www.twitter.com
[3]. A. Kumar, T. M. Sebastian, “Sentiment Analysis on Twitter”, IJCSI International Journal of Computer Science, Issue 9, No. 3 pp. 372–378, 2012.
[4]. A. Kumar, P. Dogra, V. Dabas, “Emotion Analysis Of Twitter Using Opinion Mining”, In Contemporary Computing (IC3), 2015 Eighth International Conference on, pp. 285-290, IEEE, 2015.
[5]. C. Nanda, M. Dua, “A Survey on Sentiment Analysis”, International Journal of Scientific Research in Computer Science and Engineering, Vol.5, Issue.2, pp.67-70, 2017.
[6]. L.Weng, F. Menczer, Y. Ahn, “Virality Prediction and Community Structure in Social Networks”, Nature Scientific Report, Vol. 3, Article no.2522, 2013.
[7]. T.A. Hoang, E.P.Lim, P. Achananuparp, J. Jiang, F. Zhu, “On Modeling Virality of Twitter Content”, In International Conference on Asian Digital Libraries . Springer, Berlin, Heidelberg, pp. 212-221, 2011.
[8]. J. Berger, K. Milkman, “Social transmission, emotion, and the virality of online content” Wharton Research Paper, 2010
[9]. L.K. Hansen, A. Arvidsson, F.A. Nielsen, E. Colleoni, M. Etter, “Good friends, bad news — affect and virality in Twitter” In Future information technology Springer, Berlin, Heidelberg, pp. 34-43, 2011.
[10]. D. Derks, A. E. Bos, J. V. Grumbkow, “Emoticons and social interaction on the internet: the importance of social context” Computers in Human Behavior, Vol.23, No.1, pp.842–849, 2007.
[11]. WordNet, A Lexical Database for English: https://wordnet.princeton.edu/.
[12]. A. Kumar , A. Jaiswal, “Empirical Study of Twitter and Tumblr for Sentiment Analysis using Soft Computing Techniques”, In Proceedings of the World Congress on Engineering and Computer Science 2017, Vol. 1, pp. 1-5, 2017.
[13]. MPS. Bhatia, A. Kumar, “A Primer on the Web Information Retrieval Paradigm”, Journal of Theoretical and Applied Information Technology (JATIT), Vol. 4, No.7, pp. 657-662, 2008.