Pemodelan Topik Teks Berita Menggunakan DistilBERT

  • I Made Anditya Mahesastra Universitas Udayana
  • I Dewa Made Bayu Atmaja Darmawan Universitas Udayana

Abstract

Online newspapers are content that can be a source of information or entertainment for the audience. There are so many online newspapers on the internet and also from various publishers. This condition causes the available news to be very varied and with different structures. If in certain cases we want to group these online newspapers efficiently, then a technique will be needed that will be able to group these online newspapers efficiently into several groups so that the available online newspapers can be more structured to be enjoyed according to the needs and tastes of the readers. The technique that can be applied is topic modeling. In the case of modeling the topic of Indonesian online newspapers, currently LDA is one of the most widely applied algorithms. So, this study aims to determine whether the performance of using the DistilBERT model will be better or not when compared to commonly used algorithms such as LDA for topic modeling tasks in Indonesian online newspapers.

Published
2022-11-25
How to Cite
MAHESASTRA, I Made Anditya; DARMAWAN, I Dewa Made Bayu Atmaja. Pemodelan Topik Teks Berita Menggunakan DistilBERT. Jurnal Nasional Teknologi Informasi dan Aplikasinya (JNATIA), [S.l.], v. 1, n. 1, p. 299-306, nov. 2022. Available at: <https://ojs.unud.ac.id/index.php/jnatia/article/view/92840>. Date accessed: 26 jan. 2023.

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.