Graph-of-Tweets: A Graph Merging Approach to Sub-event Identification

TL;DR

This paper introduces a hybrid Graph-of-Tweets model that combines word- and document-level structures with a graph merging technique to effectively identify sub-events on social media platforms like Twitter.

Contribution

It presents a novel method for constructing and merging graphs using FastText embeddings and Mutual Information to improve sub-event detection in social media data.

Findings

Effective in condensing lexical information

Captures keywords of sub-events accurately

Shows promising results on Twitter data

Abstract

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.