Predicting Influential Users in Online Social Network Groups

The widespread adoption of Online Social Networks (OSNs) and the ever-increasing amount of information produced by their users has led both industrial and academic researchers to focus on how such systems could be influenced.Recent results show that measuring and predicting the influence of the OSNs' users has direct applications in economy, politics, health, etc.. While previous work has mainly focused on measuring influential users, contents, or pages on the overall OSNs, the problem of predicting influencers in OSNs has remained relatively unexplored from a research perspective. Indeed, one of the main characteristics of OSNs is the ability of users to create different groups types as well as to join groups defined by other users in order to share information and opinions. In this paper, we formulate the influencers prediction problem in the context of groups created in OSNs and we define a framework to identify the influencers of the groups - i.e., the set of members who will be able to capture a higher fraction of the group's interactions. To this goal, we propose a methodology rooted on data analysis techniques and prediction models to forecast the most influential members based on historical interactions occurred within the group. We investigate the performance of our methodology to the case of 800.000 users collected from 18 Facebook groups belonging to different categories (e.g., Politics or News). Our results, rooted on solid graph theory and analytic metrics, show that the proposed methodology achieves its goal. For instance, we are able to predict, for each group, around a third of what an ex-post analysis will show being the 10 most influential members of that group. While our contribution is interesting on its own - and unique, to the best of our knowledge - it is worth noticing that it also paves the way for further research in this field.