articleJan 1, 2005GOLD OA

Recognizing contextual polarity in phrase-level sentiment analysis

University of Pittsburgh

Indexed incrossref

Abstract

This paper presents a new approach to phrase-level sentiment analysis that first determines whether an expression is neutral or polar and then disambiguates the polarity of the polar expressions. With this approach, the system is able to automatically identify the contextual polarity for a large subset of sentiment expressions, achieving results that are significantly better than baseline.

Citation impact

3,373
total citations
FWCI
59.71
Percentile
100%
References
26
Citations per year

Authors

3

Topics & keywords

Keywords
  • Polarity (international relations)
  • Phrase
  • Computer science
  • Polar
  • Sentiment analysis
  • Baseline (sea)
  • Natural language processing
  • Artificial intelligence
UN Sustainable Development Goals
  • Reduced inequalities
No related works found for this paper.

Funding