Learn More
User generated content is extremely valuable for mining market intelligence because it is unsolicited. We study the problem of analyzing users' sentiment and opinion in their blog, message board, etc. posts with respect to topics expressed as a search query. In the scenario we consider the matches of the search query terms are expanded through coreference(More)
This paper presents a rich annotation scheme for mentions , co-reference, meronymy, sentiment expressions, modifiers of sentiment expressions including neutral-izers, negators, and intensifiers, and describes a large corpus annotated with this scheme. We describe how this corpus relates to recent, state-of-the-art work in sentiment analysis, and define the(More)
Despite the preponderance of evidence that points to the advantages of prenatal care, the number of women who receive adequate prenatal care has remained at a plateau or actually decreased since 1980. Over the past decades, many demographic and structural barriers to receiving prenatal care have been identified; financial obstacles have been cited as the(More)
  • 1