Similar Event Detection and Event Topic Mining in Social Network Platform

Abstract

Social media is widely used to share information globally and it also aids to gain attention from the world. When socially sensitive incidents like rape, human rights march, corruption, political controversy, chemical attacks occur, they gain immense attention from people all over the world, causing microblogging platforms like Twitter to get flooded with tweets related to such events. When an event evolves many other events of a similar nature have happened in and around the same time frame. These are similar events because they are linked to the nature of the main event. Discussions in state-of-the-art papers are restricted to event detection, user interest discovery and detecting influential spreaders but overlook similar event detection and topic evolution. This leads to difficulty in tracing the nature of evolving events. Hence, similar event detection is critical in determining the nature of events. Similar events have fulcrums points, i.e.,topics around which the discussion is focused, as the event evolves which must be considered in topic evolution. We have proposed Event Detection model which detects similar events that are similar with regards to their temporal nature resulting from main events. The model also considers event topics, user supremacy index to calculate sub event detection factor ( $\alpha$ ). A self-tuning clustering algorithm is proposed to combine tweets, forming clusters which are composed of key posts with similar context and hence, similar topics. The sub event detection algorithm reveals events that overlap in both time and context to evaluate the effects of these similar events on deliberate human actions. The topic evolution algorithm puts into perspective the change in topics for an event's lifetime. The experimental results on a real Twitter data set demonstrate the effectiveness and precision of our proposed model for similar sub event detection during the evolution of similar events.