Analyzing the Blogosphere for Predicting the Success of Music and Movie Products

摘要

Over the last decade blogs became an important part of the Web, where people can anixounce anything that is on their mind. Due to their high popularity blogs have great potential to mine public opinions regarding products. Such knowledge is very valuable as it could be used to adjust marketing campaigns or advertisement of products accordingly: In this paper we investigate how the blogosphere can be used to predict the success of products in the domain of music and movies. We analyze and characterize the Nagging behavior in both domains particularly around product releases, propose different methods for extracting characteristic features from the blogosphere, and,show that our predictions correspond to the real world measures Sales Rank and box office revenue respectively.