The Community for Technology Leaders
Green Image
Issue No. 02 - March-April (2013 vol. 28)
ISSN: 1541-1672
pp: 22-30
Jane Yung-jen Hsu , National Taiwan University
Richard Tzong-Han Tsai , Yuan Ze University
Chi-En Wu , Yuan Ze University
Angela Charng-Rurng Tsai , National Taiwan University
ABSTRACT
Sentiment dictionaries are essential for research in the sentiment analysis field. A two-step method integrates iterative regression and random walk with in-link normalization to build a concept-level sentiment dictionary. The approach uses ConceptNet as a framework to propagate sentiment values, based on the assumption that semantically related concepts share a common sentiment.
INDEX TERMS
Knowledge discovery, Data mining, Emotion recognition, Information analysis, Knowledge discovery, Iterative methods, Data collection, Dictionaries, Context awareness, Natural language processing, commonsense knowledge, Knowledge discovery, Data mining, Emotion recognition, Information analysis, Knowledge discovery, Iterative methods, Data collection, Dictionaries, Context awareness, Natural language processing, ConceptNet, sentiment analysis, sentiment dictionary
CITATION
Jane Yung-jen Hsu, Richard Tzong-Han Tsai, Chi-En Wu, Angela Charng-Rurng Tsai, "Building a Concept-Level Sentiment Dictionary Based on Commonsense Knowledge", IEEE Intelligent Systems, vol. 28, no. , pp. 22-30, March-April 2013, doi:10.1109/MIS.2013.25
109 ms
(Ver )