International Conference on Weblogs and Social Media

Contact Information
For questions, please e-mail:


March 26-28, 2007

Large-Scale Sentiment Analysis for News and Blogs (system demonstration)

Namrata Godbole, Manjunath Srinivasaiah and Steven Skiena

News can be good or bad, but it is seldom neutral. Although full comprehension of natural language text remains well beyond the power of machines, the statistical analysis of relatively simple sentiment cues can provide a surprisingly mean- ingful sense of how the latest news impacts important entities.
Here we demonstrate our large-scale sentiment analysis system for news and blog entities built on top of the Lydia text analysis system [1]. We determine the public sentiment on each of the hundreds of thousands of entities that we track, and how this sentiment varies with time. We encourage the reader to study our historical sentiment analysis for your favorite news entities at and view daily sentiment at


Available as PDF