predicting the approximate time of event occurrence based on changes in the speed of sending messages in x social network

In recent years, the availability of virtual social network data and the mutual impact that real and virtual communities have on each other has led to much research in the field of virtual social network analysis. detecting and predicting the occurrence of social events is one of the important applications of this field. in this paper, using a threshold structure, the approximate time of the event is predicted by analyzing the messages of social network x (former twitter). in the proposed method, the data is first partitioned and preprocessed and then clustered using the distance-based chinese restaurant process. changes in the speed of sending messages to each cluster are used as an effective feature in predicting the approximate time of an event. experiments conducted on almost 5 million tweets including 876 events show a prediction accuracy of 78%.