Adam, Bima Kaka Bani (2026) Analisis Sentimen Dan Emosi Terhadap RUU Perampasan Aset Pada Komentar Youtube Menggunakan IndoBERT. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
22082010007.-cover.pdf Download (861kB) |
|
Text (Bab 1)
22082010007.-bab1.pdf Download (276kB) |
|
Text (Bab 2)
22082010007.-bab2.pdf Restricted to Repository staff only until 18 July 2028. Download (632kB) |
|
Text (Bab 3)
22082010007.-bab3.pdf Restricted to Repository staff only until 18 July 2028. Download (378kB) |
|
Text (Bab 4)
22082010007.-bab4.pdf Restricted to Repository staff only until 18 July 2028. Download (5MB) |
|
Text
22082010007.-bab5.pdf Download (171kB) |
|
Text (Daftar Pustaka)
22082010007.-daftarpustaka.pdf Download (198kB) |
|
Text (Lampiran)
22082010007.-lampiran.pdf Restricted to Repository staff only Download (391kB) |
Abstract
YouTube is a social media platform for people to express their opinions on public policy issues. Comments on the platform contain various sentiments and emotions that can be analyzed to understand public perceptions of government policies. This study aims to analyze sentiment and emotions in YouTube comments related to the Asset Forfeiture Bill using the IndoBERT model. The research method used refers to CRISP-DM, which includes Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The dataset was obtained through a process of scraping YouTube comments, followed by pre-processing stages such as cleaning, case folding, and normalization. This study uses three variants of the IndoBERT model: Indolem/indoBERT-base-uncased, indoBenchmark/indoBERT-base-p2, and IndoBERTweet with data split scenarios of 70:30 and 80:20. The results showed that the indoBenchmark/indoBERT-base-p2 model with a data split ratio of 80:20 achieved the best performance in sentiment classification with an accuracy of 92%, while in emotion classification it achieved an accuracy of 85%. Furthermore, the model was successfully implemented into a web-based application using Flask to perform automatic sentiment and emotion analysis.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||||||
| Depositing User: | Bima Kaka Bani Adam | ||||||||||||
| Date Deposited: | 20 Jul 2026 02:52 | ||||||||||||
| Last Modified: | 20 Jul 2026 04:09 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/56094 |
Actions (login required)
 |
View Item |