Entity-Based Integration Framework on Social Unrest Event Detection in Social Media

Social unrest events have been an issue of concern to people in various countries. In the past few years, mass appeared many Meanwhile, social media has become a distinctive method spreading event information. It is necessary construct effective analyze through platforms. Existing methods mainly target well-labeled data and take relatively little account development. This paper proposes entity-based integration detection framework for extraction analysis media. The integrates two modules. first module utilizes named entity recognition technology based on bidirectional encoder representation from transformers (BERT) algorithm extract event-related entities topics during communication. second suggests K-means clustering dynamic topic model (DTM) these topics. As experimental scenario, effectiveness demonstrated using Lihkg discussion forum Twitter 1 August 2019 31 2020. addition, comparative experiment performed reveal differences between Chinese users studies. results somehow indicate characteristic that can be found