Lexicon Integrated CNN Models with Attention for Sentiment Analysis

Bonggun Shin, Timothy Lee, Jinho D. Choi


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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/W17-5220.pdf
Data
SST