Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification
This work provides an incremental method for improving sub-event identification on social media, which is useful for analysts tracking real-time events.
This paper proposes a Graph-of-Tweets (GoT) model that merges word- and document-level graph structures to identify sub-events on Twitter. It uses FastText word embeddings to reduce the Graph-of-Words (GoW) and a Mutual Information (MI) measure to construct the GoT, then extracts maximal cliques to find sub-events. The model effectively condenses lexical information and captures sub-event keywords.
Graph structures are powerful tools for modeling the relationships between textual elements. Graph-of-Words (GoW) has been adopted in many Natural Language tasks to encode the association between terms. However, GoW provides few document-level relationships in cases when the connections between documents are also essential. For identifying sub-events on social media like Twitter, features from both word- and document-level can be useful as they supply different information of the event. We propose a hybrid Graph-of-Tweets (GoT) model which combines the word- and document-level structures for modeling Tweets. To compress large amount of raw data, we propose a graph merging method which utilizes FastText word embeddings to reduce the GoW. Furthermore, we present a novel method to construct GoT with the reduced GoW and a Mutual Information (MI) measure. Finally, we identify maximal cliques to extract popular sub-events. Our model showed promising results on condensing lexical-level information and capturing keywords of sub-events.