Transfer Learning of Pre-trained Transformers for Covid-19 Hoax Detection in Indonesian Language
Nowadays, internet has become the most popular source of news. However, the validity of the online news articles is difficult to assess, whether it is a fact or a hoax. Hoaxes related to Covid-19 brought a problematic effect to human life. An accurate hoax detection system is important to filter abu...
Saved in:
Main Authors: | , , |
---|---|
Format: | EJournal Article |
Published: |
IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.,
2021-07-31.
|
Subjects: | |
Online Access: | Get Fulltext Get Fulltext |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 02366 am a22003133u 4500 | ||
---|---|---|---|
001 | IJCSS_66205 | ||
042 | |a dc | ||
100 | 1 | 0 | |a Suadaa, Lya Hulliyyatus |e author |
100 | 1 | 0 | |e contributor |
700 | 1 | 0 | |a Santoso, Ibnu |e author |
700 | 1 | 0 | |a Panjaitan, Amanda Tabitha Bulan |e author |
245 | 0 | 0 | |a Transfer Learning of Pre-trained Transformers for Covid-19 Hoax Detection in Indonesian Language |
260 | |b IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia., |c 2021-07-31. | ||
500 | |a https://jurnal.ugm.ac.id/ijccs/article/view/66205 | ||
520 | |a Nowadays, internet has become the most popular source of news. However, the validity of the online news articles is difficult to assess, whether it is a fact or a hoax. Hoaxes related to Covid-19 brought a problematic effect to human life. An accurate hoax detection system is important to filter abundant information on the internet. In this research, a Covid-19 hoax detection system was proposed by transfer learning of pre-trained transformer models. Fine-tuned original pre-trained BERT, multilingual pre-trained mBERT, and monolingual pre-trained IndoBERT were used to solve the classification task in the hoax detection system. Based on the experimental results, fine-tuned IndoBERT models trained on monolingual Indonesian corpus outperform fine-tuned original and multilingual BERT with uncased versions. However, the fine-tuned mBERT cased model trained on a larger corpus achieved the best performance. | ||
540 | |a Copyright (c) 2021 IJCCS (Indonesian Journal of Computing and Cybernetics Systems) | ||
540 | |a http://creativecommons.org/licenses/by-sa/4.0 | ||
546 | |a eng | ||
690 | |a Natural Language Processing; Machine Learning; Computer Science | ||
690 | |a hoax detection, transfer learning, pre-trained transformer, Indonesian language text processing | ||
655 | 7 | |a info:eu-repo/semantics/article |2 local | |
655 | 7 | |a info:eu-repo/semantics/publishedVersion |2 local | |
655 | 7 | |2 local | |
786 | 0 | |n IJCCS (Indonesian Journal of Computing and Cybernetics Systems); Vol 15, No 3 (2021): July; 317-326 | |
786 | 0 | |n 2460-7258 | |
786 | 0 | |n 1978-1520 | |
787 | 0 | |n https://jurnal.ugm.ac.id/ijccs/article/view/66205/31845 | |
856 | 4 | 1 | |u https://jurnal.ugm.ac.id/ijccs/article/view/66205 |z Get Fulltext |
856 | 4 | 1 | |u https://jurnal.ugm.ac.id/ijccs/article/view/66205/31845 |z Get Fulltext |