Abstract: Methods and systems for extracting and analyzing user-generated content (UGC) in order to provide opinion-bearing information concerning different categories of a product. Harvested Web pages are examined for keywords to identify categories to which they pertain. Opinion-bearing information regarding those categories is then extracted and analyzed to determine its orientation and, optionally, its strength. The resulting sentiment determinations can be aggregated across multiple product reviews and the like to develop a sentiment summary, which can be reported and used as the basis for advertising, marketing and purchasing decisions, among others.