Software sorts out subjectivity

November 19, 2004 | Source: Technology Research News

Cornell University rearchers have devised a way to improve sentiment (author attitude) classification that sidesteps having to deal with meaning by instead concentrating on context. Their method weeds out neutral sentences.

The method could be used to automate the maintenance of review-aggregation sites (to extract ratings for movie reviews, for example), by search engines to sort or filter results by viewpoint, to track changes in attitudes toward a given topic, and to gather business intelligence, such as finding out what people think of a company’s products or the products of competitors.