Classifying Tweet Level Judgements of Rumours in Social Media

TL;DR

This paper presents a supervised learning approach to classify tweet-level judgments of rumours on social media, utilizing domain adaptation and multi-task learning to improve accuracy across different rumours.

Contribution

It introduces a novel framework combining supervised and unsupervised domain adaptation with multi-task learning for rumour judgment classification.

Findings

Multi-task learning improves classification accuracy.

Domain adaptation enables cross-rumour classification.

Effective on 2011 England riots dataset.

Abstract

Social media is a rich source of rumours and corresponding community reactions. Rumours reflect different characteristics, some shared and some individual. We formulate the problem of classifying tweet level judgements of rumours as a supervised learning task. Both supervised and unsupervised domain adaptation are considered, in which tweets from a rumour are classified on the basis of other annotated rumours. We demonstrate how multi-task learning helps achieve good results on rumours from the 2011 England riots.