Are Tweets Biased by Audience? An Analysis from the View of Topic Diversity
The emergence of blogs, and especially microblogs, has granted users the possibility of publishing and sharing ideas, news, opinions and any other kind of content with their audience. But this has also brought them the arduous tasks of self-censorship and adaptation of the content to an audience previously envisioned in order to keep, and even increase, their social influence. Taking into account the impossibility of knowing this imagined audience and using Twitter as a case study, we analyse if the diversity of topics chosen by users in their tweets is biased by the size of their audience. Considering the number of followers as the users’ audience and applying a methodology based on clustering the representative terms in tweets, we found that individuals with large audiences tend to deal with topics more diverse than those with small audiences. Understanding how audience size affects the range of topics chosen by a speaker have theoretical implications for sociological studies and even for the effective design of marketing campaigns.
KeywordsTopic diversity Twitter Users’ behaviour Audience
Unable to display preview. Download preview PDF.
- 2.Cilibrasi, R.L., Vitanyi, P.M.B.: The google similarity distance. IEEE Transactions on Knowledge and Data Engineering 19(3), 370–383 (2007). http://nlp.stanford.edu/software/corenlp.shtml (last accessed on December 11, 2014)
- 3.Dimitrov, A., Olteanu, A., Mcdowell, L., Aberer, K.: Topick: accurate topic distillation for user streams. In: IEEE 12th International Conference on Data Mining Workshops (ICDMW), pp. 882–885 (2012)Google Scholar
- 4.Goffman, E.: The presentation of self in everyday life (1959)Google Scholar
- 5.Jain, A.K., Dubes, R.C.: Algorithms for clustering data. Prentice-Hall, Inc. (1988)Google Scholar
- 6.Kwak, H., Lee, C., Park, H., Moon, S.: What is twitter, a social network or a news media? In: Proceedings of the 19th International Conference on World Wide Web, WWW 2010, pp. 591–600 (2010)Google Scholar
- 8.Li, R., Wang, S., Deng, H., Wang, R., Chang, K.C.C.: Towards social user profiling: unified and discriminative influence model for inferring home locations. In: KDD, pp. 1023–1031 (2012)Google Scholar
- 10.Ong, W.J.: The writer’s audience is always a fiction. Publications of the Modern Language Association of America, pp. 9–21 (1975)Google Scholar
- 11.Quercia, D., Askham, H., Crowcroft, J.: Tweetlda: supervised topic classification and link prediction in twitter. In: Proceedings of the 3rd Annual ACM Web Science Conference, WebSci 2012 (2012)Google Scholar
- 12.Rangrej, A., Kulkarni, S., Tendulkar, A.V.: Comparative study of clustering techniques for short text documents. In: Proceedings of the 20th International Conference Companion on World Wide Web, WWW 2011, pp. 111–112 (2011)Google Scholar
- 15.Servia-Rodríguez, S., Fernández-Vilas, A., Díaz-Redondo, R.P., Pazos-Arias, J.J.: Comparing tag clustering algorithms for mining twitter users’ interests. In: International Conference on Social Computing (SocialCom), pp. 679–684. IEEE (2013)Google Scholar
- 16.Witten, I., Milne, D.: An effective, low-cost measure of semantic relatedness obtained from wikipedia links. In: Proceeding of AAAI Workshop on Wikipedia and Artificial Intelligence: an Evolving Synergy, pp. 25–30 (2008)Google Scholar