TTRank: A Temporal Model to Rank Online Twitter Users

Abstract

Twitter is an online social network or a news media where users can post their desirable topical interests in the form tweets. This is a networking model where each user can choose who can follow her and whom she wants to follow. We can find the users who are very active in the social networks and consider them as influential users. This research addresses on Temporal Twitter Ranking (TTRank) to rank the influential users in Twitter. We apply Twitter-LDA topic modeling method to find the users’ topical interests. The time interval is an important factor as users’ topical interest can change over time i.e. users’ have different degree of topical interests at different timeinterval. So we give more emphasize on users’ most recent tweets. Our proposed approach also considers the impact of “Follower Influence” and “Retweet Influence”. The top influential users have been detected across different time intervals based on all the above mentioned factors and classified as “Highly Influential” and “Potential’ users. Experiment results on a real Twitter dataset demonstrate the efficacy of the proposed system.