Back close
Admissions

Learning Domain-Specific and Domain-independent Opinion Oriented Lexicons using Multi Domain Knowledge

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.

Admissions Apply Now