Mande, Afrino Battula (2025) ANALISIS SENTIMEN TERHADAP PROGRAM TABUNGAN PERUMAHAN RAKYAT DI PLATFORM X MENGGUNAKAN ALGORITMA BERT DAN BERT-SVM. S1 thesis, Universitas Mercu Buana-Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
41520120038-Afrino Battula Mande-01 Cover - AFRINO BATTULA MANDE.pdf Download (290kB) |
|
Text (BAB I)
41520120038-Afrino Battula Mande-02 Bab 1 - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (161kB) |
|
Text (BAB II)
41520120038-Afrino Battula Mande-03 Bab 2 - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (1MB) |
|
Text (BAB III)
41520120038-Afrino Battula Mande-04 Bab 3 - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (211kB) |
|
Text (BAB IV)
41520120038-Afrino Battula Mande-05 Bab 4 - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (458kB) |
|
Text (BAB V)
41520120038-Afrino Battula Mande-06 Bab 5 - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (153kB) |
|
Text (DAFTAR PUSTAKA)
41520120038-Afrino Battula Mande-07 Daftar Pustaka - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (167kB) |
|
Text (LAMPIRAN)
41520120038-Afrino Battula Mande-08 Lampiran - AFRINO BATTULA MANDE.pdf Restricted to Registered users only Download (449kB) |
Abstract
Media sosial telah menjadi platform utama bagi masyarakat untuk mengekspresikan opini terkait kebijakan pemerintah, termasuk program Tabungan Perumahan Rakyat (TAPERA) yang diatur dalam Pasal 1 PP Nomor 21 Tahun 2024. Penelitian ini bertujuan untuk menganalisis sentimen publik terhadap program TAPERA di Platform X menggunakan algoritma BERT dan BERT-SVM, serta membandingkan performa kedua algoritma tersebut dalam mengklasifikasikan sentimen menjadi tiga kategori: positif, netral, dan negatif. Data yang digunakan berupa 21.117 tweet berbahasa Indonesia yang dikumpulkan selama periode 1 Maret 2023 hingga 31 November 2024. Hasil penelitian menunjukkan bahwa algoritma BERT memiliki tingkat akurasi tertinggi sebesar 95%, mengungguli kombinasi algoritma BERT-SVM. Analisis sentimen mengungkapkan bahwa sentimen negatif mendominasi dengan 5912 tweet (42,54%) menunjukkan penerimaan yang kurang baik terhadap TAPERA, sementara sentimen netral dan positif masing-masing mencakup proporsi yang lebih kecil. Penelitian ini memberikan wawasan penting mengenai persepsi publik terhadap program TAPERA dan membuktikan keandalan BERT dalam analisis sentimen. Kata kunci Social media has become the main platform for the public to express opinions regarding government policies, including the Public Housing Savings (TAPERA) program stipulated in Article 1 of Government Regulation Number 21 of 2024. This study aims to analyze public sentiment towards the TAPERA program on Platform X using the BERT and BERT-SVM algorithms, and compare the performance of the two algorithms in classifying sentiment into three categories: positive, neutral, and negative. The data used is 21,117 Indonesian tweets collected during the period March 1, 2023 to November 31, 2024. The results show that the BERT algorithm has the highest accuracy rate of 95%, outperforming the BERT-SVM algorithm combination. Sentiment analysis revealed that negative sentiment dominated with 5912 tweets (42.54%) indicating unfavorable reception towards TAPERA, while neutral and positive sentiments each accounted for a smaller proportion. This research provides important insights into public perception of the TAPERA program and proves the reliability of BERT in sentiment analysis. Keywords : TAPERA, sentiment
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41520120038 |
| Uncontrolled Keywords: | TAPERA, analisis sentimen, BERT, BERT-SVM, media sosial, Platform X. TAPERA, sentiment analysis, BERT, BERT-SVM, social media, Platform XTAPERA, sentiment analysis, BERT, BERT-SVM, social media, Platform X. |
| 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: | RAUL ANDIKA KURNIAWAN |
| Date Deposited: | 31 Jan 2025 04:50 |
| Last Modified: | 31 Jan 2025 04:50 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/93788 |
Actions (login required)
 |
View Item |
