Lexicon-Based Methods for Sentiment Analysis
Top Cited Papers
Open Access
- 1 June 2011
- journal article
- Published by MIT Press in Computational Linguistics
- Vol. 37 (2), 267-307
- https://doi.org/10.1162/coli_a_00049
Abstract
We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.Keywords
This publication has 22 references indexed in Scilit:
- THE DYNAMICS OF SELLER REPUTATION: EVIDENCE FROM EBAY*Journal of Industrial Economics, 2010
- Appraisal of Opinion Expressions in DiscoursePublished by John Benjamins Publishing Company ,2009
- A Lexicon-Enhanced Method for Sentiment Classification: An Experiment on Online Product ReviewsIEEE Intelligent Systems, 2009
- Language patterns and ATTITUDEInterpersonal Meaning, 2009
- Negativity bias in language: A cognitive-affective model of emotive intensifiersCognitive Linguistics, 2007
- SENTIMENT CLASSIFICATION of MOVIE REVIEWS USING CONTEXTUAL VALENCE SHIFTERSComputational Intelligence, 2006
- Recognizing subjectivity: a case study in manual taggingNatural Language Engineering, 1999
- Adverbial stance types in EnglishDiscourse Processes, 1988
- Affect, mood, emotion, and feeling: semantic considerationsAmerican Journal of Psychiatry, 1975
- The pollyanna hypothesisJournal of Verbal Learning and Verbal Behavior, 1969