Sentiment Analysis for e-Services

New e-services come on-line each year at an exponential rate. Most of them have the need to analyze and interpret enormous quantities of data. However, many of them do not take into account the emotions and sentiments in the Web page for their analysis. Thus, in this work, we proposed a novel system to obtain data of interest from a Web search engine by analyzing the emotional and sentimental content of each page. This information can provide a new way to identify the community response to a product: Given the positive vs negative average sentimental rates in the forums, it is possible to know the Web community perception to the product. In addition, this classification makes possible to identify the best sales options given a certain product, and it also permits to obtain a great reduction in the needed time to find the best options by grouping the comparison pages for an easy access. Thus, we believe that this system is the beginning of a new way to help the user in their selection of the best product to buy, and it makes possible to have a better understanding on how the users perceive the recommended products.