Abstract
With the advent of word embeddings, lexicons are no longer fully utilized for sentiment analysis although they still provide important features in the traditional setting. This paper introduces a novel approach to sentiment analysis that integrates lexicon embeddings and an attention mechanism into Convolutional Neural Networks. Our approach performs separate convolutions for word and lexicon embeddings and provides a global view of the document using attention. Our models are experimented on both the SemEval’16 Task 4 dataset and the Stanford Sentiment Treebank and show comparative or better results against the existing state-of-the-art systems. Our analysis shows that lexicon embeddings allow building high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.- Anthology ID:
- W17-5220
- Volume:
- Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Venue:
- WASSA
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 149–158
- Language:
- URL:
- https://aclanthology.org/W17-5220
- DOI:
- 10.18653/v1/W17-5220
- Cite (ACL):
- Bonggun Shin, Timothy Lee, and Jinho D. Choi. 2017. Lexicon Integrated CNN Models with Attention for Sentiment Analysis. In Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 149–158, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- Lexicon Integrated CNN Models with Attention for Sentiment Analysis (Shin et al., WASSA 2017)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/W17-5220.pdf
- Data
- SST