Sentiment Clustering: A Novel Method to Explore in the Blogosphere

An emotion-oriented clustering approach is proposed according to the sentiment similarities between blog search result titles and snippets to allow for better organization and easy navigation, which provides users a novel method to explore in the blogosphere.

Abstract

In recent years, blogs have become the major platform for people to express their opinions and sentiments in the Web age. The traditional blog search engines usually employ topic-oriented techniques, which are not easy for users to make better understanding of bloggers' feelings and emotions. In this paper, an emotion-oriented clustering approach is proposed according to the sentiment similarities between blog search result titles and snippets. Extensive experiments were conducted based on a real world blog search engine and the experiments show that our approach can cluster blog search result items into sentiment groups to allow for better organization and easy navigation, which provides users a novel method to explore in the blogosphere.