Hongcheng Mi, I-Heng Mei
Sentiment mining is a computational approach used to identify expressions made about topics within a span of text. The blogosphere is a particularly useful corpus for sentiment mining because bloggers express a wide variety of opinions and sentiments in their online journals. Previous works on sentiment identification and extraction have been primarily focused on using machine-learning methods to extract sentiment patterns. Annotating text corpuses, however, is a time-consuming process. In this paper, we present a streamlined approach to extract sentiments from untagged text. We use heuristic models to quickly identify sentiment expressions and target subjects. This is an enabling approach to the rapid identification and extraction of expressions about topics.