Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification

Authors

  • Zeyang Lei Tsinghua University
  • Yujiu Yang Tsinghua University
  • Min Yang Shenzhen Institutes of Advanced Technology,¬†Chinese Academy of Sciences

Keywords:

sentiment classification, multi-head attention, sentiment lexicon

Abstract

Deep neural networks have gained great success recently for sentiment classification. However, these approaches do not fully exploit the linguistic knowledge. In this paper, we propose a novel sentiment lexicon enhanced attention-based LSTM (SLEA-LSTM) model to improve the performance of sentence-level sentiment classification. Our method successfully integrates sentiment lexicon into deep neural networks via single-head or multi-head attention mechanisms. We conduct extensive experiments on MR and SST datasets. The experimental results show that our model achieved comparable or better performance than the state-of-the-art methods.

Downloads

Published

2018-04-29

How to Cite

Lei, Z., Yang, Y., & Yang, M. (2018). Sentiment Lexicon Enhanced Attention-Based LSTM for Sentiment Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12142