Event prediction in social network through Twitter messages analysis

Event detection using social media analysis has attracted researchers' attention. Prediction of events especially in the management of social crises can be of particular significance. In this study, events are predicted through analyzing Twitter messages and examining the changes in the rate of Tweets in a specified subject. In the proposed method, the Tweets are initially preprocessed in consecutive fixed-length time windows. Tweets are then categorized using the non-negative matrix factorization analysis and the distance dependent Chinese restaurant process incremental clustering. The categorization results show that a high rate of Tweets entering a cluster represents the occurrence of a new event in near future. Finally, a description of the event is presented in the form of some frequent words in each cluster. In this paper, investigations on a Tweet dataset during a 6-month period indicate that the rate of sending Tweets about predictable events considerably changes before their occurrence. The use of this feature can make it possible to predict events with high degrees of precision.