Social Networks

One of the fruitful fields within computer science today, Social Network Analysis (SNA), proliferated thanks to the many online social networks and active engagement of their users. Think of Twitter, Facebook, LinkedIn, Flickr, Swarm etc. SNA in particular enabled analysing some of the classical sociological theories within this new, online context. Hence, a synergy between sociology and computer science is asked for, and the new field termed Computation Social Science emerged. Our research belongs to this field.

Homophily in communication

Homophily is a tendency of similar individuals to connect. The famous saying illustrates is it simply: birds of a feather flock together. Homophily has been known already earlier in sociology, however recent SNA studies confirmed and quantified it on a large scale and in diverse settings.

We investigated homophily in Twitter communication on the basis of semantic features of users’ communication content, and also based on their social status in the Twitter network.

  1. In other words, for semantics, we asked, whether users who in general talk on similar topics talk more to each other. Then we also looked at specific topics, and measured for which of them this tendency is more pronounced.  We also found that users of similar sentiment talk more to each other.
  2. The question for social status is in simple words whether those who are more central and important in the social network tend to talk to others who are also more central and important. The answer is again positive.

While these results are expected from the knowledge from sociology from before, we extended the insights into the relationship between social status and semantic features of user tweets. In that regard, we find that the users who are more active and popular tend to use more diverse semantic content. At the same time, the most active users tend to have negative sentiment of their tweets.

A novel aspect of our study is that we investigated homophily on interaction links: based on mentions between users, instead of only following.  In this way, instead of one time and persisting links, we could assign the strength to the links and also we could define when they are formed or disconnected. Thanks to this approach, we found that for users to start communicating, it is important that their tweet topics are similar (value homophily); while, at the same time, the reason for disconnection of once an active link is more likely to be their status difference (status heterophily) than differences in topics.

Šćepanović S., Mishkovski I., Gonçalves B., Nguyen Trung Hieu, Hui P. “Semantic homophily in online communication: evidence from Twitter“, Online Social Network and Media, Elsevier, 2017 (to appear).