Paper: A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection

ACL ID P14-2113
Title A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

We investigate the novel task of online dis- pute detection and propose a sentiment analy- sis solution to the problem: we aim to identify the sequence of sentence-level sentiments ex- pressed during a discussion and to use them as features in a classifier that predicts the DISPUTE/NON-DISPUTE label for the dis- cussion as a whole. We evaluate dispute de- tection approaches on a newly created corpus of Wikipedia Talk page disputes and find that classifiers that rely on our sentiment tagging features outperform those that do not. The best model achieves a very promising F1 score of 0.78 and an accuracy of 0.80.