Publication Type:

Conference Paper

Source:

Sixth International Conference on Contemporary Computing (IC3-2014), IEEE (2014)

URL:

http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6897193

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.

207
PROGRAMS
OFFERED
5
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
8th
RANK(INDIA):
NIRF 2018
150+
INTERNATIONAL
PARTNERS