Back close

An Efficient Word Embedded Click-Bait Classification of YouTube Titles Using SVM

Publication Type : Conference Proceedings

Publisher : Symposium on Machine Learning and Metaheuristics Algorithms, and Applications SoMMA 2019: Machine Learning and Metaheuristics Algorithms, and Applications, Part of the Communications in Computer and Information Science book series (CCIS), Springer Science and Business Media LLC

Source : Symposium on Machine Learning and Metaheuristics Algorithms, and Applications SoMMA 2019: Machine Learning and Metaheuristics Algorithms, and Applications, Part of the Communications in Computer and Information Science book series (CCIS), Springer Science and Business Media LLC, Volume 1203, p.175–184 (2020)

Url : https://link.springer.com/chapter/10.1007%2F978-981-15-4301-2_15

Campus : Amritapuri

School : Department of Computer Science and Engineering, School of Engineering

Department : Computer Science

Year : 2020

Abstract : Most of the online media outlets normally depend on the revenues generated from the clicks made by their viewers and due to presence of their outlets. To increase traffic onto their websites some people come with some misleading headlines as titles for their links. Such misleading headlines are known as Click-baits. These click-baits leave the user disappointed as the content of the address is very different from the headline or the title. The current work focuses on classification of YouTube titles into click-baits and non click-baits using tokenization and word embedding applied to SVM. Upon simulation of the algorithm we are able to increase the accuracy, compared to some of the other classification algorithms.

Cite this Research Publication : K. V. Sankar Reddy, K. Nihith, S., Krishna Prasad T. R., and M. Chowdary, S., “An Efficient Word Embedded Click-Bait Classification of YouTube Titles Using SVM”, Symposium on Machine Learning and Metaheuristics Algorithms, and Applications SoMMA 2019: Machine Learning and Metaheuristics Algorithms, and Applications, Part of the Communications in Computer and Information Science book series (CCIS), vol. 1203. Springer Science and Business Media LLC, pp. 175–184, 2020.

Admissions Apply Now