Scrutable Feature Sets for Stance Classification

Mandya, Angrosh; Siddharthan, Advaith and Wyner, Adam (2016). Scrutable Feature Sets for Stance Classification. In: Proceedings of the 3rd Workshop on Argument Mining, pp. 60–69.

URL:	http://www.aclweb.org/anthology/W/W16/W16-2807.pdf
Google Scholar:	Look up in Google Scholar

Abstract

This paper describes and evaluates a novel feature set for stance classification of argumentative texts; i.e. deciding whether a post by a user is for or against the issue being debated. We model the debate both as attitude bearing features, including a set of automatically acquired ‘topic terms’ associated with a Distributional Lexical Model (DLM) that captures the writer’s attitude towards the topic term, and as dependency features that represent the points being made in the debate. The stance of the text towards the issue being debated is then learnt in a supervised framework as a function of these features. The main advantage of our feature set is that it is scrutable: The reasons for a classification can be explained to a human user in natural language. We also report that our method outperforms previous approaches to stance classification as well as a range of baselines based on sentiment analysis and topic-sentiment analysis.

Item Type:	Conference or Workshop Item
Copyright Holders:	2016 Association for Computational Linguistics
Extra Information:	Originally presented at ArgMining2016: the Third Workshop on Argument Mining, Berlin, Germany, 7-12 Aug 2016.
Academic Unit/School:	Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi) Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID:	58725
Depositing User:	Advaith Siddharthan
Date Deposited:	23 Jan 2019 09:56
Last Modified:	29 Mar 2019 11:02
URI:	http://oro.open.ac.uk/id/eprint/58725
Share this page:

Actions (login may be required)

CORE (COnnecting REpositories)

Policies | Disclaimer