Lexicon Integrated CNN Models with Attention for Sentiment Analysis

• Bonggun Shin ^[1] ; Timothy Lee ^[1] ; Jinho D. Choi ^[1]
  1. [1] Emory University

     Emory University

     Estados Unidos

     
• Localización: 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis WASSA 2017: Proceedings of the Workshop / Alexandra Balahur Dobrescu (ed. lit.), Saif M. Mohammad (ed. lit.), Erik van der Goot (ed. lit.), 2017, ISBN 978-1-945626-95-1, págs. 149-158
• Idioma: inglés
• Enlaces
  • Texto completo (pdf)
• Resumen

  • With the advent of word embeddings, lex- icons are no longer fully utilized for sen- timent 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 pro- vides 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 al- low building high-performing models with much smaller word embeddings, and the attention mechanism effectively dims out noisy words for sentiment analysis.