Lexicon-Enhanced LSTM With Attention for General Sentiment Analysis

TLDR: A lexicon-enhanced LSTM model that first uses sentiment lexicon as an extra information pre-training a word sentiment classifier and then gets the sentiment embeddings of words including the words not in the lexicon to make word representation more accurate.

Abstract: Long short-term memory networks (LSTMs) have gained good performance in sentiment analysis tasks. The general method is to use LSTMs to combine word embeddings for text representation. However, word embeddings carry more semantic information rather than sentiment information. Only using word embeddings to represent words is inaccurate in sentiment analysis tasks. To solve the problem, we propose a lexicon-enhanced LSTM model. The model first uses sentiment lexicon as an extra information pre-training a word sentiment classifier and then get the sentiment embeddings of words including the words not in the lexicon. Combining the sentiment embedding and its word embedding can make word representation more accurate. Furthermore, we define a new method to find the attention vector in general sentiment analysis without a target that can improve the LSTM ability in capturing global sentiment information. The results of experiments on English and Chinese datasets show that our models have comparative or better results than the existing models.