Deriving market intelligence from microblogs

Given their rapidly growing popularity, microblogs have become great sources of consumer opinions. However, in the face of unique properties and the massive volume of posts on microblogs, this paper proposes a framework that provides a compact numeric summarization of opinions on such platforms. The proposed framework is designed to cope with the following tasks: trendy topics detection, opinion classification, credibility assessment, and numeric summarization. An experiment is carried out on Twitter, the largest microblog website, to prove the effectiveness of the proposed framework. We find that the consideration of user credibility and opinion subjectivity is essential for aggregating microblog opinions. The proposed mechanism can effectively discover market intelligence (MI) for supporting decision-makers.

► We propose a framework that provides a compact numeric summarization of opinions on microblogs.
► Trendy topics detection, sentiment classification, credibility assessment are considered.
► User credibility and opinion quality is essential for aggregating microblog opinions.
► The proposed mechanism discovers market intelligence for supporting decision-makers.