Stance classification with target-specific neural attention networks

Jiachen Du, Ruifeng Xu*, Yulan He, Lin Gui

*Corresponding author for this work

Research output: Chapter in Book/Published conference outputConference publication

Abstract

Stance classification, which aims at detecting the stance expressed in text towards a specific target, is an emerging problem in sentiment analysis. A major difference between stance classification and traditional aspect-level sentiment classification is that the identification of stance is dependent on target which might not be explicitly mentioned in text. This indicates that apart from text content, the target information is important to stance detection. To this end, we propose a neural network-based model, which incorporates target-specific information into stance classification by following a novel attention mechanism. In specific, the attention mechanism is expected to locate the critical parts of text which are related to target. Our evaluations on both the English and Chinese Stance Detection datasets show that the proposed model achieves the state-of-the-art performance.

Original languageEnglish
Title of host publication26th International Joint Conference on Artificial Intelligence, IJCAI 2017
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3988-3994
Number of pages7
ISBN (Electronic)9780999241103
DOIs
Publication statusPublished - 25 Aug 2017
Event26th International Joint Conference on Artificial Intelligence, IJCAI 2017 - Melbourne, Australia
Duration: 19 Aug 201725 Aug 2017

Conference

Conference26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Country/TerritoryAustralia
CityMelbourne
Period19/08/1725/08/17

Bibliographical note

IJCAI International Joint Conference on Artificial Intelligence2017, Pages 3988-399426th International Joint Conference on Artificial Intelligence, IJCAI 2017; Melbourne; Australia; 19 August 2017 through 25 August 2017; Code 130864

Fingerprint

Dive into the research topics of 'Stance classification with target-specific neural attention networks'. Together they form a unique fingerprint.

Cite this