Abstract
Sentiment analysis seeks to identify the viewpoint(s) underlying a text span; an example application is classifying a movie review as "thumbs up" or "thumbs down". To determine this sentiment polarity, we propose a novel machine-learning method that applies text-categorization techniques to just the subjective portions of the document. Extracting these portions can be implemented using efficient techniques for finding minimum cuts in graphs; this greatly facilitates incorporation of cross-sentence contextual constraints.
Keywords
Computer scienceCategorizationSentiment analysisPolarity (international relations)SentenceArtificial intelligenceNatural language processingText categorizationMachine learning
Affiliated Institutions
Related Publications
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding
Human ability to understand language is general, flexible, and robust. In contrast, most NLU models above the word level are designed for a specific task and struggle with out-o...
Publication Info
- Year
- 2004
- Type
- article
- Pages
- 271-es
- Citations
- 3318
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3318
OpenAlex
Cite This
Bo Pang,
Lillian Lee
(2004).
A sentimental education.
, 271-es.
https://doi.org/10.3115/1218955.1218990
Identifiers
- DOI
- 10.3115/1218955.1218990