Fuzzy sentiment analysis on microblogs for movie revenue prediction

Abstract

With the advent of microblogging in recent years, people voice their views about products, especially movies. Microblogs are rich sources of data that can be analyzed to derive useful knowledge like larger public opinion on a product, which can be utilized to derive sales performance patterns. In this paper we propose a novel fuzzy approach for evaluating sentiments expressed in microblogs, which are incorporated in text mining methodologies to predict weekly movie revenues.