PENGARUH NORMALISASI TEKS TERHADAP ANALISIS SENTIMEN BERBASIS INDOBERTWEET PADA TWEET TENTANG RUU TNI

Zakiyah, Isnaeni (2025) PENGARUH NORMALISASI TEKS TERHADAP ANALISIS SENTIMEN BERBASIS INDOBERTWEET PADA TWEET TENTANG RUU TNI. Tugas Akhir (S1) - thesis, Universitas Bakrie.

	Text (Cover) 00.Cover.pdf - Accepted Version Download (683kB)
	Text (BAB I-III) 01. BAB I-III.pdf - Accepted Version Restricted to Registered users only Download (1MB) | Request a copy
	Text (BAB IV) 02. BAB IV.pdf - Accepted Version Restricted to Registered users only Download (6MB) | Request a copy
	Text (BAB V) 03. BAB V.pdf - Accepted Version Restricted to Registered users only Download (125kB) | Request a copy
	Text (BAB Daftar Pustaka) 04. BAB Daftar Pustaka.pdf - Accepted Version Download (135kB)

Abstract

This study examines the effect of text normalization on sentiment analysis performance of tweets regarding the revision of the TNI Bill. The dataset consists of 8,603 tweets collected through web crawling between March 29 and April 4, 2025. Preprocessing steps included cleaning, case folding, and normalization, followed by automatic labeling into three sentiment classes: positive, neutral, and negative. The IndoBERTweet model was tested in two scenarios, normalized and non-normalized datasets. Performance was evaluated using accuracy, precision, recall, and F1-score. The results reveal that text normalization does not consistently improve model performance. In certain cases, non-normalized data achieved comparable or even better outcomes. The study concludes that the impact of normalization is highly contextual, depending on data characteristics and the chosen model. These findings contribute to the development of Indonesian sentiment analysis in socio-political domains and suggest further research with ensemble learning and domain-adaptive pretraining. Keywords: Sentiment Analysis, IndoBERTweet, Text Normalization, Social Media, RUU TNI

Item Type:	Thesis (Tugas Akhir (S1) - )
Uncontrolled Keywords:	Analisis Sentimen, IndoBERTweet, Normalisasi Teks, Media Sosial, RUU TNI
Subjects:	Computer Science > Informatics Computer Science > Information analysis Thesis > Thesis (S1)
Divisions:	Fakultas Teknik dan Ilmu Komputer > Program Studi Informatika
Depositing User:	Isnaeni Zakiyah
Date Deposited:	04 Sep 2025 03:23
Last Modified:	04 Sep 2025 03:23
URI:	https://repository.bakrie.ac.id/id/eprint/12112

Actions (login required)

View Item