Automating Opinion Analysis in Film Reviews: The Case of Statistic Versus Linguistic Approach

摘要: Websites dedicated to collecting and disseminating opinions about goods, services, ideas,attract a diversity of comprising attitudes emotions. www.flixster.com is an example participative web site, where enthusiastic reviewers share their feelings/views on movies– usually expressing polar opinions. The web-sites contain substantial amount data which continually been updated.The contents such websites regarded as key source information by academic commercial researchers keen gauge this sample public opinion. challenge automatically extract the Our goal use reviews for building model can then be used predict user’s verdict movie. We explore two different methods extracting first, machine learning method that uses naive Bayesian classifier. second builds upon existing NLP techniques process build dictionaries: those dictionaries are determine polarity comment review. compare contrast relative merits with special reference movie review bases.