Publication: Opinion classification on a social network by a novel feature selection technique
Submitted Date
Received Date
Accepted Date
Issued Date
2020
Copyright Date
Announcement No.
Application No.
Patent No.
Valid Date
Resource Type
Edition
Resource Version
Language
en
File Type
No. of Pages/File Size
ISBN
ISSN
2502-4760
eISSN
Scopus ID
WOS ID
Pubmed ID
arXiv ID
item.page.harrt.identifier.callno
Other identifier(s)
Journal Title
Indonesian Journal of Electrical Engineering and Computer Science
Volume
20
Issue
2
Edition
Start Page
960
End Page
967
Access Rights
Access Status
Rights
Copyright (c) 2020 Institute of Advanced Engineering and Science
Rights Holder(s)
Physical Location
Bibliographic Citation
Research Projects
Organizational Units
Authors
Journal Issue
Title
Opinion classification on a social network by a novel feature selection technique
Alternative Title(s)
Author’s Affiliation
Author's E-mail
Editor(s)
Editor’s Affiliation
Corresponding person(s)
Creator(s)
Compiler
Advisor(s)
Illustrator(s)
Applicant(s)
Inventor(s)
Issuer
Assignee
Other Contributor(s)
Series
Has Part
Abstract
Most of the opinion comments on social networks are short and ambiguous. In general; opinion classification on the comments is difficult because of lacking dominant features. A feature extraction technique is therefore necessary for improving accuracy of the classification and computational time. This paper proposes an effective feature selection method for opinion classification on a social network. The proposed method selects features based on the concept of a filter model; together with association rules. Support and confidence are used to calculate the weights of features. The features with high weight are selected for classification. Unlike supports in association rules; supports in our method are normalized to 0-1 to remove outlier supports. Moreover; a tuning parameter is used to emphasize the degree of support or confidence. The experimental results show that the proposed method provides high classification efficiency. The proposed method outperforms Information Gain; Chi-Square; and Gini Index in both computational time and accuracy.