A Modified Metaheuristic Algorithm for Opinion Mining
Opinion mining is a recent discipline combining Information Retrieval and Computational Linguistics which is concerned with the opinion a document expresses and not just with the topic in the document. Online forums, newsgroups, blogs, and specialized sites provide voluminous information feeds from where opinions can be retrieved. Opinion's polarity is established through application of machine learning techniques for classification of textual reviews as either a positive or negative class. In this paper, it is proposed to extract the feature set from reviews using Inverse document frequency and the reviews are classified as positive or negative using Bagging algorithms. The proposed method is evaluated using a subset of Internet Movie DataBase (IMBd).