High Level Event Identification in Social Media

The rapid growth of information technology along with variety of digital data generation provides an opportunity to better understand human dynamics. However, knowing and obtaining complete information about events and activities that happen, becomes a complicated task in Natural Language Processing (NLP) and location based social networks. In this research, we introduce a new approach to recognize events in social media. On the basis of the approach, we demonstrate an event explorer system which models event topics using a latent Dirichlet allocation (LDA) and classifies the events by various features. The preliminary result is introduced on certain web-sources. The study aims at improving automatic event recognition task from social media.