Lexical Based Semantic Orientation of Online Customer Reviews and Blogs-J-Am Sci 10(8) 143_147--07-june-2014.pdf

<div>Rapid increase in internet users along with growing power of online review sites and social media has</div><div>given birth to sentiment analysis or opinion mining, which aims at determining what other people think and</div><div>comment. Sentiments or Opinions contain public generated content about products, services, policies and politics.</div><div>People are usually interested to seek positive and negative opinions containing likes and dislikes, shared by users for</div><div>features of particular product or service. This paper proposed sentence-level lexical based domain independent</div><div>sentiment classification method for different types of data such as reviews and blogs. The proposed method is based</div><div>on general lexicons i.e. WordNet, SentiWordNet and user defined lexical dictionaries for semantic orientation. The</div><div>relations and glosses of these dictionaries provide solution to the domain portability problem. The method performs</div><div>better than word and text level corpus based machine learning methods for semantic orientation. The results show</div><div>the proposed method performs better as it shows precision of 87% and 83% at document and sentence levels</div><div>respectively for online comments.