Open AccessOpinion mining using combinational approach for different domains
Author(s) -
Jyoti S Deshmukh,
Amiya Kumar Tripathy,
Dilendra Hiran
Publication year - 2019
Publication title -
international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.277
H-Index - 22
ISSN - 2088-8708
DOI - 10.11591/ijece.v9i4.pp3307-3313
Subject(s) - computer science , domain (mathematical analysis) , domain adaptation , data mining , cluster analysis , entropy (arrow of time) , task (project management) , artificial intelligence , machine learning , classifier (uml) , mathematics , mathematical analysis , physics , management , quantum mechanics , economics
An increase in use of web produces large content of information about products. Online reviews are used to make decision by peoples. Opinion mining is vast research area in which different types of reviews are analyzed. Several issues are existing in this area. Domain adaptation is emerging issue in opinion mining. Labling of data for every domain is time consuming and costly task. Hence the need arises for model that train one domain and applied it on other domain reducing cost aswell as time. This is called domain adaptation which is addressed in this paper. Using maximum entropy and clustering technique source domains data is trained. Trained data from source domain is applied on target data to labeling purpose A result shows moderate accuracy for 5 fold cross validation and combination of source domains for Blitzer et al (2007) multi domain product dataset.