Twitter in academic events: A study of temporal usage, communication, sentimental and topical patterns in 16 Computer Science conferences

Abstract

Twitter is often referred to as a backchannel for conferences. While the main conference takes place in a physical setting, on-site and off-site attendees socialize, introduce new ideas or broadcast information by microblogging on Twitter. In this paper we analyze the scholars’ Twitter usage in 16 Computer Science conferences over a timespan of five years. Our primary finding is that over the years there are differences with respect to the uses of Twitter, with an increase of informational activity (retweets and URLs), and a decrease of conversational usage (replies and mentions), what also impacts the network structure — the amount of connected components — of the information and conversation networks. We also applied topic modeling over the tweets’ content and found that when clustering conferences according to their topics the resulting dendrogram clearly resembles the similarities and differences of the actual research interests of those events. Furthermore, we also analyzed the sentiment of tweets and found persistent differences among conferences, showing that some communities consistently express messages with emotions while others do it more neutrally. Finally, we investigated features that can help to predict future user participation to the online Twitter conference activity. By casting the problem as a classification task, we created a model that identifies factors that contribute to the continuing user participation. Our results have implications for research communities to implement strategies for continuous and active participation among members. Moreover, our work reveals the potential for using information shared on Twitter to facilitate the work of research communities, such as discovering resources or researchers from relevant but barely known research communities.