ASPECT BASED SENTIMENT ANALYSIS OF HINDI TEXT REVIEW

Abstract

Sentiment analysis (SA) is one of the fastest growing research areas in Natural Language Processing, making it challenging to keep track of all the activities in the area. Increase in user-generated content (UGC) has provided an important aspect for the researchers, industries and government(s) to mine this information. SA mine information from UGC on the basis of polarity as positive, negative or neutral. The problem domain, to which this research is concerned, is to find the sentiment and its respective aspect in the sentence and finally to calculate the overall sentiment score of entered Hindi text to classify each sentence as positive, negative and neutral. In this thesis, we work on the sentiment analysis by devolving an algorithm that identifying the sentiment according to proposed rules based on positions of conjunction, negation and aspects (nouns).