Rahma, Dea Ananda Refiza Analisis Sentimen Publik menggunakan VADER Sentiement, Topic Modeling Latent Dirichlet Allocation (LDA), dan Random Forest pada Website Berita: Studi Kasus Timnas Indonesia. Project Report (Praktek Kerja Lapang dan Magang). UPN Veteran Jawa Timur. (Unpublished)
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
COVER.pdf Download (2MB) |
|
Text (Bab I)
BAB I.pdf Download (464kB) |
|
Text (Bab II)
BAB II.pdf Restricted to Repository staff only until 9 July 2028. Download (587kB) |
|
Text (Bab III)
BAB III.pdf Restricted to Repository staff only until 9 July 2028. Download (693kB) |
|
Text (Bab IV)
BAB IV.pdf Restricted to Repository staff only until 9 July 2028. Download (3MB) |
|
Text (Bab V)
BAB V.pdf Download (387kB) |
|
Text (Daftar Pustaka)
DAFTAR PUSTAKA (2).pdf Download (329kB) |
|
Text (Lampiran)
LAMPIRAN.pdf Restricted to Repository staff only Download (983kB) |
Abstract
The development of information technology has made news websites a primary source of information, including news coverage about the Indonesian National Football Team. This study aims to analyze public sentiment toward news coverage of the Indonesian National Team by combining VADER Sentiment analysis, topic modeling using Latent Dirichlet Allocation (LDA), and the Random Forest algorithm. The data were collected from trusted news websites, such as CNN, Bola.com, Kompas.com, Detik.com, and Suara.com, through web scraping techniques, resulting in a dataset consisting of news titles, publication dates, and article contents. VADER Sentiment was used to classify sentiment into positive, negative, and neutral categories. Furthermore, LDA was applied to identify the main topics frequently discussed in news coverage related to the Indonesian National Team. The results of the topic analysis were then integrated with Random Forest to develop a predictive model capable of classifying sentiment based on relevant textual features. The findings show that public sentiment toward news coverage of the Indonesian National Team is predominantly neutral, with sentiment distribution influenced by the team’s achievements, performance, and related controversies. In addition, the most dominant topics include match performance, coaching strategies, and participation in international competitions. The Random Forest model demonstrated good accuracy in predicting sentiment, indicating the relevance of topic-based features in sentiment analysis. This study is expected to provide insights for relevant stakeholders, such as the management of the Indonesian National Team and media organizations, in understanding public perception and improving their communication strategies.
| Item Type: | Monograph (Project Report (Praktek Kerja Lapang dan Magang)) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||
| Divisions: | Faculty of Computer Science > Departemen of Information Systems | ||||||||
| Depositing User: | Dea Ananda Refiza Rahma | ||||||||
| Date Deposited: | 20 Jul 2026 06:18 | ||||||||
| Last Modified: | 20 Jul 2026 06:18 | ||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/54948 |
Actions (login required)
 |
View Item |