DETEKSI KATA KASAR DALAM LIRIK LAGU BERBAHASA INGGRIS MENGGUNAKAN MODEL BERT

ARYADINATA, BIMA and Yusliani, Novi and Rachmatullah, Muhammad Naufal (2025) DETEKSI KATA KASAR DALAM LIRIK LAGU BERBAHASA INGGRIS MENGGUNAKAN MODEL BERT. Undergraduate thesis, Sriwijaya University.

	Image RAMA_55201_09021282126035_cover.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (571kB)
	Text RAMA_55201_09021282126035.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021282126035_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (893kB)
	Text RAMA_55201_09021282126035_0008118205_0001129204_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (455kB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (286kB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_06.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (182kB)
	Text RAMA_55201_09021282126035_0008118205_0001129204_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (190kB) | Request a copy
	Text RAMA_55201_09021282126035_0008118205_0001129204_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (119kB) | Request a copy

Abstract

Music plays a significant role through digital streaming platforms, while concerns about offensive language in lyrics, especially among young listeners, require attention. This study develops a BERT-based model to detect offensive language in English song lyrics. The dataset comprises 3,598 lyrics, divided into training 2,878 data, validation 360 data, and test 360 data. Experiments tested 12 parameter scenarios involving variations in learning rate 2e-5, 3e-6, 5e-5, batch size 16 and 32, and freeze layers 6 and 8. Evaluation used confusion matrix and metrics including accuracy, precision, recall, and F1-score. Results showed the model detected offensive language with 93.06% accuracy using learning rate 3e-6, batch size 16, and 8 freeze layers, demonstrating BERT's effectiveness for this task despite some classification errors due to sentence structure similarities.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Offensive Language Detection, Song Lyrics, BERT, NLP Model, Music Streaming
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Bima Aryadinata
Date Deposited:	19 May 2025 08:11
Last Modified:	19 May 2025 08:11
URI:	http://repository.unsri.ac.id/id/eprint/173236

Actions (login required)

View Item