Leveraging Target-Oriented Information for Stance Classification

Classifying the stance expressed in text towards specific target, namely stance detection, is a challenging task. The biggest distinction between stance detection and ordinary sentiment classification is that the determination of the stance is dependent on target while the target might not be explicitly mentioned in text. This indicates that the stance detection is not only dependent on the text content but also highly determined by the concerned target. To this end, we propose a neural network based model for stance detection, which leverages target-oriented information by utilizing target-augmented embedding and attention mechanism. The attention mechanism here is expected to locate the important parts of a text. The evaluation on SemEval 2016 Task 6 Twitter Stance Detection dataset shows that our proposed model achieves the state-of-the-art results.

[1]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[2]  Li Zhao,et al.  Attention-based LSTM for Aspect-level Sentiment Classification , 2016, EMNLP.

[3]  Marilyn A. Walker,et al.  Stance Classification using Dialogic Properties of Persuasion , 2012, NAACL.

[4]  Adam Faulkner,et al.  Automated Classification of Stance in Student Essays: An Approach Using Stance Target Information and the Wikipedia Link-Based Measure , 2014, FLAIRS.

[5]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[6]  Christopher D. Manning,et al.  Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks , 2015, ACL.

[7]  Andreas Vlachos,et al.  Emergent: a novel data-set for stance classification , 2016, NAACL.

[8]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[9]  Saif Mohammad,et al.  SemEval-2016 Task 6: Detecting Stance in Tweets , 2016, *SEMEVAL.

[10]  Ruifeng Xu,et al.  Extracting Opinion Expression with Neural Attention , 2016, SMP.

[11]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[12]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[13]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[14]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[15]  Soroush Vosoughi,et al.  DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs , 2016, *SEMEVAL.

[16]  Qin Lu,et al.  Intersubjectivity and Sentiment: From Language to Knowledge , 2016, IJCAI.

[17]  Ting Liu,et al.  Document Modeling with Gated Recurrent Neural Network for Sentiment Classification , 2015, EMNLP.

[18]  Vincent Ng,et al.  Stance Classification of Ideological Debates: Data, Models, Features, and Constraints , 2013, IJCNLP.

[19]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[20]  Marilyn A. Walker,et al.  Cats Rule and Dogs Drool!: Classifying Stance in Online Debate , 2011, WASSA@ACL.

[21]  Kalina Bontcheva,et al.  Stance Detection with Bidirectional Conditional Encoding , 2016, EMNLP.