Stance classification with target-specific neural attention networks


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.

Publication DOI:
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
?? 50811700Jl ??
Additional Information: 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
Event Title: 26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Event Type: Other
Event Dates: 2017-08-19 - 2017-08-25
Uncontrolled Keywords: Artificial Intelligence
ISBN: 9780999241103
Last Modified: 18 Apr 2024 07:31
Date Deposited: 24 May 2017 11:00
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2017-08-25
Accepted Date: 2017-08-25
Authors: Du, Jiachen
Xu, Ruifeng
He, Yulan (ORCID Profile 0000-0003-3948-5845)
Gui, Lin



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record