A General Method for Event Detection on Social Media

TL;DR

This paper introduces a versatile event detection method for social media that relies on semantic behavior changes during events, outperforming traditional approaches especially for unusual events.

Contribution

It presents a generalized, assumption-light algorithm for detecting social media events using word embeddings and time series analysis.

Findings

Effective at detecting unusual real-world news events.

Outperforms baseline methods on novel evaluation setting.

Easily implementable as a foundational tool.

Abstract

Event detection on social media has attracted a number of researches, given the recent availability of large volumes of social media discussions. Previous works on social media event detection either assume a specific type of event, or assume certain behavior of observed variables. In this paper, we propose a general method for event detection on social media that makes few assumptions. The main assumption we make is that when an event occurs, affected semantic aspects will behave differently from its usual behavior. We generalize the representation of time units based on word embeddings of social media text, and propose an algorithm to detect events in time series in a general sense. In the experimental evaluation, we use a novel setting to test if our method and baseline methods can exhaustively catch all real-world news in the test period. The evaluation results show that when the event is quite unusual with regard to the base social media discussion, it can be captured more effectively with our method. Our method can be easily implemented and can be treated as a starting point for more specific applications.