Publication Type : Conference Paper
Publisher : Sixth International Conference on Contemporary Computing (IC3-2014)
Source : Sixth International Conference on Contemporary Computing (IC3-2014), IEEE (2014)
Url : http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6897193
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science
Year : 2014
Abstract : Sentiment analysis systems are used to know the opinions of customer reviews. The basic resource for the sentiment analysis systems are polarity lexicon. Each term in polarity lexicon indicates its affinity towards positive or negative opinion. However, this affinity of word changes with the change in domain. In this work, we explore a polarity lexicon using SentiWordNet, a domain independent lexicon to adapt specific domain and update the domain independent lexicon based on multiple domain knowledge. The proposed approach has been tested on five domains: Health, Books, Camera, Music and DVD. The improvement in accuracy ranges from 4.5 to 19 pointsacross all the domains over baseline.
Cite this Research Publication : K. S. Vishnu, Apoorva, T., and Dr. Deepa Gupta, “Learning Domain-Specific and Domain-independent Opinion Oriented Lexicons using Multi Domain Knowledge”, in Sixth International Conference on Contemporary Computing (IC3-2014), 2014.