Feature extracted sentiment analysis of customer product reviews

Online shopping is more and more common nowadays. The growth in its popularity has led to increase in customer reviews that a product receives. A customer who has to choose the right product among the huge varieties of products, depends heavily on the product reviews to make a purchase decision. With great volume of product reviews, it become difficult for customers to wade through all reviews to make an informed product choice. Nowadays customers look for features that can serve them specifically. But from the thousands of reviews, it is practically impossible for customers to identify the reviews which speak about the specific product feature. As a solution to these problems, in this work we aim to analyze a product at feature level, from the customer product reviews. The proposed system, follows a semantic based approach to extract product features. An algorithm, which employ typed dependencies, is introduced for this purpose. Recursive Deep model is used to identify sentiment orientation of review sentences. A review matrix is constructed to find the importance and polarity of each product feature. The experimental results show that the method proposed is effective and has achieved the desired objective.