Review Mining: A New Approach using Modified NLP

Abstract

The Web has become an excellent source for gathering consumer opinions. There are now numerous Web sites containing such opinions, e.g., customer reviews of products, forums, discussion groups, and blogs. Nowadays we get all the technical specifications of a product on the Web, but what matters is what the customer feels about or what his opinions about the product are. This paper focuses on analyzing and summarizing online customer reviews of products. While analyzing we devise a new approach for NLP, by assigning a latent weight to each aspect/feature of a product. After extracting the sentiment in each sentence of the review, we summarize the opinions and express it graphically. This will not only help customers but also help the product manufacturers to get an indirect customer feedback.