ANALISIS SENTIMEN PUBLIK TERHADAP PROGRAM MAKAN SIANG GRATIS MENGGUNAKAN BERT NEURAL NETWORK PADA PLATFORM X

ILHAM, MUHAMAD (2025) ANALISIS SENTIMEN PUBLIK TERHADAP PROGRAM MAKAN SIANG GRATIS MENGGUNAKAN BERT NEURAL NETWORK PADA PLATFORM X. S1 thesis, Universitas Mercu Buana Jakarta.

Text (JURNAL MAHASISWA) Jurnal 41521010029 Muhamad Ilham.pdf Restricted to Registered users only Download (1MB)

Abstract

The government’s free lunch program aims to improve the nutrition of school children, pregnant women, and toddlers. However, this program faces significant challenges, including potential fiscal burden, risk of food wastage, and distribution issues. This study aims to understand public response to the program through sentiment analysis on platform X (Twitter) using the BERT model, indolem/indobert-base-uncased. A dataset of 1,739 tweets was analyzed following processes of data collection, preprocessing, tokenization, model training, and evaluation. The model achieved an accuracy of 86.2%, precision of 86.4%, recall of 76.1%, and f1-score of 80.9%. The analysis reveals that negative sentiment dominates, with the majority of users expressing skepticism regarding the program’s effectiveness and sustainability. These findings provide valuable insights into public perceptions, offering guidance for improving policy implementation. Kata kunci: free lunch program, sentiment analysis, Twitter, BERT, deep learning Program makan siang gratis yang diluncurkan pemerintah bertujuan untuk meningkatkan gizi anak sekolah, ibu hamil, dan balita. Namun, program ini menghadapi tantangan signifikan, termasuk potensi beban fiskal yang tinggi, risiko pemborosan, dan kendala distribusi. Penelitian ini bertujuan untuk memahami respons masyarakat terhadap program tersebut melalui analisis sentimen di platform X (Twitter) menggunakan model BERT, indolem/indobert-base-uncased. Data sebanyak 1.739 tweet dianalisis setelah melalui proses pengumpulan, preprocessing, tokenisasi, pelatihan, dan evaluasi model. Hasil pengujian model menunjukkan akurasi sebesar 86,2%, precision 86,4%, recall 76,1%, dan f1-score 80,9%. Analisis ini mengungkapkan bahwa sentimen negatif mendominasi, dengan mayoritas pengguna menunjukkan skeptisisme terhadap efektivitas dan keberlanjutan program. Temuan ini memberikan wawasan penting mengenai persepsi publik yang dapat menjadi masukan untuk peningkatan implementasi kebijakan. Kata kunci: program makan siang gratis, analisis sentimen, Twitter, BERT, deep learning

Item Type:	Thesis (S1)
Call Number CD:	JM/INFO. 25 005
NIM/NIDN Creators:	41521010029
Uncontrolled Keywords:	program makan siang gratis, analisis sentimen, Twitter, BERT, deep learning
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 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 > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.32 Neural Nets (Neural Network)/Jaringan Saraf Buatan 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 153 Conscious Mental Process and Intelligence/Intelegensia, Kecerdasan Proses Intelektual dan Mental > 153.1 Memory and Learning/Memori dan Pembelajaran > 153.15 Learning/Pembelajaran 300 Social Science/Ilmu-ilmu Sosial > 300. Social Science/Ilmu-ilmu Sosial > 303 Social Process/Proses Sosial > 303.3 Coordination and Control/Koordinasi dan Kontrol > 303.38 Public Opinion/Opini Publik
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	13 Feb 2025 01:48
Last Modified:	13 Feb 2025 01:48
URI:	http://repository.mercubuana.ac.id/id/eprint/94164

Actions (login required)

View Item