ET-LDA: Joint Topic Modeling For Aligning, Analyzing and Sensemaking of Public Events and Their Twitter Feeds

TL;DR

ET-LDA is a joint topic modeling approach that effectively aligns Twitter feeds with public events, segments events into meaningful parts, and categorizes tweets as episodic or steady, enhancing understanding of social media responses.

Contribution

This work introduces ET-LDA, a novel joint statistical model for aligning, segmenting, and categorizing tweets in relation to public events, with improved accuracy and interpretability.

Findings

User study shows 18-41% improvement in quality and interest of topics and segments.

ET-LDA outperforms existing methods in event-tweet alignment and segmentation.

Model effectively distinguishes episodic and steady tweets, aiding event analysis.

Abstract

Social media channels such as Twitter have emerged as popular platforms for crowds to respond to public events such as speeches, sports and debates. While this promises tremendous opportunities to understand and make sense of the reception of an event from the social media, the promises come entwined with significant technical challenges. In particular, given an event and an associated large scale collection of tweets, we need approaches to effectively align tweets and the parts of the event they refer to. This in turn raises questions about how to segment the event into smaller yet meaningful parts, and how to figure out whether a tweet is a general one about the entire event or specific one aimed at a particular segment of the event. In this work, we present ET-LDA, an effective method for aligning an event and its tweets through joint statistical modeling of topical influences from the events and their associated tweets. The model enables the automatic segmentation of the events and the characterization of tweets into two categories: (1) episodic tweets that respond specifically to the content in the segments of the events, and (2) steady tweets that respond generally about the events. We present an efficient inference method for this model, and a comprehensive evaluation of its effectiveness over existing methods. In particular, through a user study, we demonstrate that users find the topics, the segments, the alignment, and the episodic tweets discovered by ET-LDA to be of higher quality and more interesting as compared to the state-of-the-art, with improvements in the range of 18-41%.