Twitter Event Summarization by Exploiting Semantic Terms and Graph Network

Twitter is a fast communication channel for gathering and spreading breaking news, it generates large volume of tweets most events. Automatically creating summary an event necessary important. In this study, we explored two extractive approaches summarizing events on Twitter. The first one exploits the semantic types related terms, ranks based score computed from these terms. second utilizes graph convolutional network built tweet relation to generate hidden features salience estimation. And salient are selected as event. Our experiments show that outperform compared methods.