Sentiment Lexicon Expansion using Word2vec and fastText for Sentiment Prediction in Tamil texts

Abstract

Sentiment Analysis is the process of identifying and categorising the sentiments expressed in a text into positive or negative. The words which carry the sentiments are the keys in sentiment prediction. The SentiWordNet is the sentiment lexicon used to determine the sentiment of texts. There are huge number of sentiment terms that are not in the SentiWordNet limit the performance of Sentiment Analysis. Gathering and grouping such sentiment words manually is a tedious task. In this paper we propose a sentiment lexicon expansion method using Word2vec and fastText word embeddings along with rule-based Sentiment Analysis method. We expand the sentiment lexicon from the initial seed list of 2951 positive and 5598 negative words in two steps: (i) Gathering related words using Word2vec word embedding and (ii) Gathering lexically similar words using fastText word embedding. Our final lexicons UJ_Lex_Pos and UJ_Lex_Neg ended up with 10537 positive and 12664 negative words respectively which are labelled using Word2vec word embedding. Furthermore the rule-based Sentiment Analysis method uses expanded lexicons (UJ_Lex_Pos and UJ_Lex_Neg), lists of conjunctions and negational words to predict the sentiments expressed in Tamil texts. The method is evaluated on UJ_MovieReviews and an accuracy of 88 0.14% is obtained.