Prof. Sara Owsley Sood's research is the subject of article in the on-line version of Scientific American
Prof. Sara Owsley Sood's research on web content and emotion with Elizabeth Churchill, a principal research scientist at Yahoo, is the subject of the September 29 article, “Sentiment-sensing software could aid in weeding hostile online comments,” in the on-line version of Scientific American.
Their research team has developed a “sentiment engine” to analyze the works used across comment threads. “The researchers distinguished off-topic negative comments from on-topic negative comments that, while critical, are offered in the spirit of debate,” explains the article.
“The approach was to combine relevance analyses for detecting on and off-topic comments with sentiment detection methods that broke comments down into three broad categories: happy, sad and angry. Sentiment analysis is a Web site-specific problem—the same words that are perfectly fine to describe the weather (cold, hot, etc.) have a different meaning when they are used to describe people, for example.”
View original source:
http://www.scientificamerican.com/blog/post.cfm?id=sentiment-sensing-software-could-ai-2010-09-29