Author : Seema Kolkur, Gayatri Dantal and Reena Mahe

With the evolution of web technology, online shopping has become very popular as it is convenient and time saving. It also provides platform to share experiences and provide feedback. These opinions reflect whether the product is good or bad and helps to make decisions by potential customers. Sentiment analysis is the procedure by which information can be extracted from these reviews, analyzed and categorized as positive, negative or neutral. It is the combination of natural language processing and information extraction system. Main goal of Sentiment analysis is to train computer to be able to understand, recognize and generate emotions. This paper gives an overview of different levels on which sentiment analysis can be performed.

Keywords: Reviews, Polarity, Sentiment Analysis, Sentence level, Document level, Feature level etc.

Article published in International Journal of Current Engineering and Technology, Vol.5, No.2 (April-2015)