DocumentCode :
234753
Title :
Learning domain-specific and domain-independent opinion oriented lexicons using multiple domain knowledge
Author :
Vishnu, K. Sai ; Apoorva, T. ; Gupta, Deepika
Author_Institution :
Dept. of Comput. Sci., Amrita VishwaVidhyapeetham, Bangalore, India
fYear :
2014
fDate :
7-9 Aug. 2014
Firstpage :
318
Lastpage :
323
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.
Keywords :
learning (artificial intelligence); semantic Web; text analysis; SentiWordNet; domain independent lexicon; multiple domain knowledge; opinion oriented lexicon learning; polarity lexicon; sentiment analysis systems; Cameras; DVD; Lead; Manuals; Three-dimensional displays; Opinion Oriented Words; SentiWordNet; domain- independent lexicon; domain-specific lexicon; polarity lexicon;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Contemporary Computing (IC3), 2014 Seventh International Conference on
Conference_Location :
Noida
Print_ISBN :
978-1-4799-5172-7
Type :
conf
DOI :
10.1109/IC3.2014.6897193
Filename :
6897193
Link To Document :
بازگشت