Events Detection and Temporal Analysis in Social Media

In the past few years, event detection has drawn a lot of attention. We proposed an efficient method to detect event in this paper. An event is defined as a set of descriptive, collocated keywords in this paper. Intuitively, documents that describe the same event will contain similar sets of keywords. Individual events will form clusters in the graph of keywords for a document collection. We built a network of keywords based on their co-occurrence in documents. We proposed an efficient method which create a keywords weight directed graph named KeyGraph and use community detection method to discover events. Clump of keywords describing an event can be used to analyse the trend of the event. The accuracy of detecting events is over eighty percents with our method.