Sentiment Analysis About Indonesian Lawyers Club Television Program Using K-Nearest Neighbor, Naïve Bayes Classifier, And Decision Tree

Wilim, Nico Nathanael and Oetama, Raymond Sunardi (2021) Sentiment Analysis About Indonesian Lawyers Club Television Program Using K-Nearest Neighbor, Naïve Bayes Classifier, And Decision Tree. International Journal of New Media Technology, 8 (1). pp. 50-56. ISSN 2581-1851

Full text not available from this repository.

Abstract

Indonesia Lawyers Club (ILC) is a talk show on TVOne that discusses topics around public phenomena, legal issues, crime, and other similar topics. In 2018, ILC won the Panasonic Gobel Awards as the best news talk show program. But in 2019, ILC failed to win the award which was won by Mata Najwa which featured a talk show event that appeared on Trans7. As one of the television shows that has won awards, ILC has pros and cons for its shows from the public. This study applies a sentiment analysis approach to examine public opinion on Twitter about Mata Najwa and ILC in 2018 and 2019. This study applies K-Nearest Neighbor, Naïve Bayes Classifier, and Decision Tree classification algorithm to validate the result. The contribution of this study is to show that public opinion on Twitter can be examined to figure out community sentiment on a tv talk show as well as to confirm the Award winner of tv Talkshow.

Item Type: Article
Keywords: datamining; Decision Tree; K-NN; Naïve Bayes Classifier; sentiment analysis
Subjects: 000 Computer Science, Information and General Works > 000 Computer Science, Knowledge and Systems > 006 Special Computer Methods
000 Computer Science, Information and General Works > 070 News Media, Journalism and Publishing > 070 News, mass media, journalism, and publishing
600 Technology (Applied Sciences) > 600 Technology > 607 Education, Research, Related Topics
Divisions: Faculty of Engineering & Informatics > Information System
Depositing User: Administrator UMN Library
Date Deposited: 25 Nov 2021 09:25
Last Modified: 29 Jun 2022 03:18
URI: https://kc.umn.ac.id/id/eprint/19293

Actions (login required)

View Item View Item