Sentiment Mining and Indexing in Opinmind

I-Heng Mei, Hongcheng Mi and Julius Quiaot

This paper presents a production system that efficiently mines social networking sites for sentiments and indexes the expressions for fast retrieval via a web search interface. Sentiment mining is a computational approach used to identify expressions made about topics within a span of text. Social networks represent a particularly rich corpus for mining sentiments because writers express sentiments about a wide variety of topics in their online journals. We introduce a streamlined approach to extract sentiment expressions and target subjects from unstructured and grammatically imperfect text. In addition, we discuss our approach to index sentiment expressions.

Demo

Available as PDF