Stance classification with target-specific neural attention

Du, Jiachen; Xu, Ruifeng; He, Yulan and Gui, Lin Stance classification with target-specific neural attention. IN: IJCAI 2017 proceedings. UNSPECIFIED. (In Press)

Abstract

Classifying stance expressed in a text toward specific target is an emerging problem in opinion mining. A major difference between stance detection and traditional aspect-level sentiment classification is that the target of the stance might not be explicitly mentioned in text. In this paper, we show that the stance polarity of a text is not merely dependent on the content but is also highly determined by the concerned target. To this end, We propose a neural network based model, which incorporate target-specific information into stance classification using a novel attention mechanism. The proposed attention mechanism can focus on critical parts of a text. We evaluate our model on the SemEval 2016 Task 6 Twitter Stance Detection corpus achieving satisfactory performance. Our model achieves significant and consistent improvements on this task as compared with baselines.

Divisions: Engineering & Applied Sciences > Computer science
Engineering & Applied Sciences > Non-linearity and complexity research group
Engineering & Applied Sciences > Computer science research group
Engineering & Applied Sciences > Systems analytics research institute (SARI)
Additional Information: -
Event Title: 26th International Joint Conference on Artificial Intelligence (IJCAL 2017)
Event Type: Other
Event Dates: 2017-08-19 - 2017-08-25

Download

Full text not available from this repository.

Export / Share Citation


Statistics

Additional statistics for this record