Hindi Sentiment Analysis

Abstract

With the evolution of web technology, a huge amount of data is present on the web. In addition to exploring the resources present on web, the users also provide feedback thus generating additional useful data. Thus mining of data and identifying user sentiments is the need of the hour. Sentiment analysis is the natural language processing task that mines information from various text forms such as blogs, reviews and classify them on the basis of polarity such as positive, negative or neutral. Hindi is the national language of India and is spoken by 366 million people across the world. The percentage of web content in Hindi is growing at lightning speed. A lot of research in opinion mining is carried out in English language but there are not many instances of research done in Hindi language. In this paper we have proposed a strategy for classifying given Hindi texts in to different classes and then extract sentiments in terms of positive, negative and neutral for identified classes. Naive Bayes, Modified Maximum entropy are used for classification and HindiSentiWordNet (HSWN) is used to determine the polarity of individual class.