A Radial Basis Function Approach for Opinion Mining

As the world becomes more oriented towards the Internet, online reviews are a popular way to check the prevailing opinion about a product. The customer's feedback on websites, blogs, influences the decision of other customers. The businesses keep track of the feedback to develop marketing strategies and upgrade products and services. Opinion mining mines the feedback available at different forums such as review websites, discussion forums and blogs. It is an efficient way to automatically extract and process reviews and provide a summary of the required information. In this paper it is proposed to extract the feature set from movie opinions. Inverse document frequency is computed and the feature set is reduced using the proposed correlation based on feature reduction. Theproposed preprocessing method efficacy is tested using Naive Bayes and Radial Basis Function classifier.