Detecting Clickbait Titles in YouTube Indonesia Using Naïve Bayes Classifier

Jonathan Gunawan
Faculty of Life Science, Human Computer Interaction Surya University Tangerang, Indonesia
Zahra Putri Agusta
Faculty of Life Science, Human Computer Interaction Surya University Tangerang, Indonesia








Abstract

Many content creator on YouTube rely heavily from the revenues from their videos, due to the high amount of content creators on YouTube makes the competition even tighter. To attract the viewers to watch their videos, they need to make some catchy titles for the videos. Which are also known as ‘Clickbait’. Currently the use of clickbait in YouTube Indonesia has become more common. Viewers are often disappointed with videos that do not meet their expectations, eventually they will only waste their time and resources. Machine learning is an appropriate method for solving this problem. Therefore, in this work Naïve Bayes classifier is used to detect clickbait title on YouTube Indonesia. Naïve Bayes classifier will predict the outcome of each words from the title whether those words are clickbait or not. Besides the machine learning method, preprocessing also needed in this research to process the raw data before it will be trained with the machine learning. With those method applied on this study, we can achieve recall to classify clickbait title up to 91%. This study was conducted with a hope to reduce the amount of clickbait titles in YouTube in Indonesia.




Download Paper
PDF

Publication Date

27/11/2018


ISBN

978-602-53524-0-9


Copyright


© The authors.
This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/


RSS Feed
Feed

Download Paper

647 times.


Share




Proceeding The 2nd International Conference on Informatics for Development
27 November 2018
ISBN 978-602-53524-0-9
Open Access