Skip to main content

Research Repository

Advanced Search

Connecting Targets to Tweets: Semantic Attention-based Model for Target-Specific stance Detection

Zhou, Yiwei; Cristea, Alexandra I.; Shi, Lei; Bouguettaya, Athman; Gao, Yunjun; Klimenko, Andrey; Chen, Lu; Zhang, Xiangliang; Dzerzhinskiy, Fedor; Jia, Weijia; Klimenko, Stanislav V.; Li, Qing

Connecting Targets to Tweets: Semantic Attention-based Model for Target-Specific stance Detection Thumbnail


Authors

Yiwei Zhou

Lei Shi

Athman Bouguettaya

Yunjun Gao

Andrey Klimenko

Lu Chen

Xiangliang Zhang

Fedor Dzerzhinskiy

Weijia Jia

Stanislav V. Klimenko

Qing Li



Abstract

Understanding what people say and really mean in tweets is still a wide open research question. In particular, understanding the stance of a tweet, which is determined not only by its content, but also by the given target, is a very recent research aim of the community. It still remains a challenge to construct a tweet’s vector representation with respect to the target, especially when the target is only implicitly mentioned, or not mentioned at all in the tweet. We believe that better performance can be obtained by incorporating the information of the target into the tweet’s vector representation. In this paper, we thus propose to embed a novel attention mechanism at the semantic level in the bi-directional GRU-CNN structure, which is more fine-grained than the existing token-level attention mechanism. This novel attention mechanism allows the model to automatically attend to useful semantic features of informative tokens in deciding the target-specific stance, which further results in a conditional vector representation of the tweet, with respect to the given target. We evaluate our proposed model on a recent, widely applied benchmark Stance Detection dataset from Twitter for the SemEval-2016 Task 6.A. Experimental results demonstrate that the proposed model substantially outperforms several strong baselines, which include the state-of-the-art token-level attention mechanism on bi-directional GRU outputs and the SVM classifier.

Citation

Zhou, Y., Cristea, A. I., Shi, L., Bouguettaya, A., Gao, Y., Klimenko, A., …Li, Q. (2017). Connecting Targets to Tweets: Semantic Attention-based Model for Target-Specific stance Detection. In Web Information Systems Engineering -- WISE 2017 (18-32). https://doi.org/10.1007/978-3-319-68783-4_2

Conference Name Web Information Systems Engineering – WISE 2017, 18th International Conference
Conference Location Moscow
Acceptance Date Jul 28, 2017
Online Publication Date Oct 4, 2017
Publication Date Oct 4, 2017
Deposit Date Jul 11, 2018
Publicly Available Date Oct 4, 2018
Pages 18-32
Series Title Lecture notes in computer science
Series Number 10569
Series ISSN 0302-9743
Book Title Web Information Systems Engineering -- WISE 2017
DOI https://doi.org/10.1007/978-3-319-68783-4_2
Related Public URLs http://wrap.warwick.ac.uk/90807/

Files

Accepted Conference Proceeding (533 Kb)
PDF

Copyright Statement
The final publication is available at Springer via https://doi.org/10.1007/978-3-319-68783-4_2







You might also like



Downloadable Citations