Jurnal Computer Science and Information Technology (CoSciTech)
Vol 4 No 1 (2023): Jurnal Computer Science and Information Technology (CoSciTech)

Klasifikasi Clickbait Menggunakan Transformers

Mori Hovipah Mori Hovipah (Unknown)
Elin Hearani (Universitas Islam Negeri Sultan Syarif Kasim Riau)
Jasril Jasril (Universitas Islam Negeri Sultan Syarif Kasim Riau)
Fadhilah Syafria (Universitas Islam Negeri Sultan Syarif Kasim Riau)



Article Info

Publish Date
30 Apr 2023

Abstract

Clickbait is a news title created by the author with the aim of attracting the getting to get readers so they Never miss a headline. Clickbait headlines are typically quirky, confusing, and use exaggerated sentences to entice readers to click on links. However, clickbait headlines that look very attractive often do not match the information in the headlines and the content of the news, which can lead to the spread of fake news and hoaxes. Then classification of clickbait news titles is carried out, for this research, clickbait classification was carried out for news titles will be carried out using the Transformers method. The number of news titles used in this study amounted to 6632 news titles. The process of classification of news titles in this study includes: collecting data, labeling data, preprocessing, EDA, and classification using transformers. The best accuracy value obtained in this study was 63% for precision of 0.63 and recall of 1 using a data division of 10%: 90%.

Copyrights © 2023






Journal Info

Abbrev

coscitech

Publisher

Subject

Computer Science & IT

Description

Jurnal CoSciTech (Computer Science and Information Technology) merupakan jurnal peer-review yang diterbitkan oleh Program Studi Teknik Informatika, Fakultas Ilmu Komputer, Univeritas Muhammadiyah Riau (UMRI) sejak April tahun 2020. Jurnal CoSciTech terdaftar pada PDII LIPI dengan Nomor ISSN ...