A Supervised Method for Constructing Sentiment Lexicon in Persian Language

Due to the increasing growth of digital content on the internet and social media, sentiment analysis problem is one of the emerging fields. This problem deals with information extraction and knowledge discovery from textual data using natural language processing has attracted the attention of many researchers. Construction of sentiment lexicon as a valuable language resource is a one of the important fields of study in this domain. The main researches in the area of sentiment analysis have focused on English language and few works considered the sentiment analysis in Persian language due to the lack of resources. This paper aims to introduce a supervised method for creating a sentiment dictionary in Persian language with extracting linguistic features in reviews and statistical mutual information to determine the sentiment orientation and sentistrength of words. To evaluate the proposed method, a set of existing reviews in the online retail site is used in various domains and the present dictionary is compared with Sentiwordnet. The results show the proposed method achieves an accuracy of 80% in determining the orientation of sentiment word.