Jin, Wei and Ho, Hung Hay
Merchants selling products on the Web often ask their customers to share their opinions and hands-on experiences on products they have purchased. As e-commerce is becoming more and more popular, the number of customer reviews a product receives grows rapidly. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. In this research, we aim to mine the customer reviews of a product and extract highly specific product related entities on which reviewers express their opinions. Opinion expressions and sentences are also identified and opinion orientation for each recognized product entity is classified as positive or negative. Different from previous approaches mostly rely on natural language processing techniques (e.g., dependency grammars) or statistic information (e.g., association rules), we propose a novel machine learning framework using lexicalized HMMs. The approach naturally integrates linguistic features, such as part-of-speeches and surrounding contextual clues of words into the learning framework. The experimental results demonstrate the effectiveness of the proposed approach in web opinion mining and extraction from product reviews.
Discussion