Manihuruk, Afriando Halven (2025) Analisis Sentimen Masyarakat Terhadap Danantara Sebagai Superholding Nasional Menggunakan Algoritma IndoBERTweet. S1 thesis, Universitas Mercu Buana Jakarta - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (Cover)
41521010208-AFRIANDO HALVEN MANIHURUK-01 Cover - AFRIANDO HALVEN MANIHURUK.pdf Download (353kB) |
|
Text (BAB I)
41521010208-AFRIANDO HALVEN MANIHURUK-02 Bab 1 - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (106kB) |
|
Text (BAB II)
41521010208-AFRIANDO HALVEN MANIHURUK-03 Bab 2 - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (138kB) |
|
Text (BAB III)
41521010208-AFRIANDO HALVEN MANIHURUK-04 Bab 3 - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (144kB) |
|
Text (Daftar Pustaka)
41521010208-AFRIANDO HALVEN MANIHURUK-05 Bab 4 - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (4MB) |
|
Text (BAB IV)
41521010208-AFRIANDO HALVEN MANIHURUK-06 Bab 5 - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (85kB) |
|
Text (BAB V)
41521010208-AFRIANDO HALVEN MANIHURUK-08 Daftar Pustaka - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (166kB) |
|
Text (Lampiran)
41521010208-AFRIANDO HALVEN MANIHURUK-09 Lampiran - AFRIANDO HALVEN MANIHURUK.pdf Restricted to Registered users only Download (789kB) |
Abstract
Penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap Danantara sebagai Superholding Nasional melalui opini publik di media sosial Twitter dengan menggunakan algoritma IndoBERTweet. Danantara merupakan lembaga investasi strategis yang baru dibentuk oleh pemerintah Indonesia, sehingga menimbulkan beragam opini publik yang perlu dianalisis untuk mengetahui persepsi masyarakat secara objektif. Data dikumpulkan sebanyak 2.596 tweet dengan kata kunci “Danantara” menggunakan teknik crawling. Selanjutnya, data diproses melalui tahapan pra-pemrosesan teks seperti pembersihan URL, simbol, dan huruf kapital, kemudian dilakukan tokenisasi, pelabelan otomatis menggunakan model IndoBERTweet, dan dibagi menjadi data latih serta data uji. Hasil klasifikasi menunjukkan bahwa sentimen netral mendominasi dengan persentase 57,9%, diikuti sentimen positif sebesar 36,3%, dan sentimen negatif sebesar 5,8%. Evaluasi model menghasilkan akurasi sebesar 93% dengan nilai precision, recall, dan F1-score yang tinggi di semua kategori sentimen, membuktikan bahwa IndoBERTweet efektif dalam mengolah data opini publik berbahasa Indonesia yang bersifat informal. Penelitian ini tidak hanya memberikan gambaran umum tentang persepsi publik terhadap Danantara, tetapi juga menunjukkan potensi model IndoBERTweet sebagai alat analisis sentimen yang andal untuk konteks kebijakan nasional. This study aims to analyze public sentiment toward Danantara as a National Superholding through public opinion on the social media platform Twitter using the IndoBERTweet algorithm. Danantara is a newly established strategic investment institution by the Indonesian government, which has sparked various public opinions that need to be analyzed objectively to understand public perception. A total of 2,596 tweets containing the keyword "Danantara" were collected using a web crawling technique. The data were then processed through several preprocessing steps, including the removal of URLs, symbols, and capitalization, followed by tokenization, automatic labeling using the IndoBERTweet model, and splitting into training and testing datasets. The classification results show that neutral sentiment dominates with a proportion of 57.9%, followed by positive sentiment at 36.3%, and negative sentiment at 5.8%. Model evaluation yielded an accuracy of 93%, with high precision, recall, and F1- scores across all sentiment categories, indicating that IndoBERTweet is effective in processing informal Indonesian-language opinion data from social media. This study not only provides an overview of public perception toward Danantara but also demonstrates the potential of IndoBERTweet as a reliable sentiment analysis tool in the context of national policy discourse.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41521010208 |
| Uncontrolled Keywords: | Analisis Sentimen, Danantara, IndoBERTweet, Twitter, Opini Publik. Sentiment Analysis, Danantara, IndoBERTweet, Twitter, Public Opinion. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | ZAIRA ELVISIA |
| Date Deposited: | 04 Sep 2025 04:18 |
| Last Modified: | 04 Sep 2025 04:21 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/97433 |
Actions (login required)
 |
View Item |
