Persian Sentiment Lexicon Expansion Using Unsupervised Learning Methods

Abstract

Sentiment analysis, is a subfield of natural language processing that aims at opinion mining to analyze thoughts, orientation and, evaluation of users within some texts. The solution to this problem includes two main steps: extracting aspects and determining users’ positive or negative sentiments with respect to the aspects. Two main challenges of sentiment analysis in the Persian language are lack of comprehensive tagged data sets and use of colloquial language in texts. In this paper we propose, a system to specify and extract sentiment words using unsupervised methods in the Persian language that also support colloquial words. Additionally, we also proposed and implemented a state-of-art technique to expand Persian sentiment lexicon. Our proposed method utilized neural network (Word2Vec model) with the help of rule-based methods. F1 measure for sentiment words extraction in our proposed method is 0.58.