Semantic orientation approach for sentiment classification

Opinions are the fundamental aspect to almost all decision making activities. The increased usage of internet and the exchange of user opinions through social media and public forums on the web has become the motivation for sentiment analysis. Due to the infinite amount of user opinions available throughout the web it is necessary to automatically analyze and classify sentiment expressed in opinions. The basic task of sentiment analysis or opinion mining is sentiment classification which classifies the content as positive, negative and irrelevant. This paper discusses an approach where an exposed stream of tweets from the Twitter micro blogging site are preprocessed and classified based on their sentiments. In sentiment classification system the concept of opinion subjectivity has been accounted. In this paper, we present opinion detection and organization subsystem, which have already been integrated into our larger question-answering system. The subjectivity classification system uses Genetic-Based Machine Learning (GBML) technique that considers subjectivity as a semantic problem. The classification of a review is predicted through the average semantic orientation of the phrases in the review that contain adjectives or adverbs. Experimental results of the proposed techniques are efficient and generate eminent evaluations.