Analisis sentimen komentar terhadap Indonesia Emas 2045 pada media sosial TikTok menggunakan BERT

Chen, Excel (2025) Analisis sentimen komentar terhadap Indonesia Emas 2045 pada media sosial TikTok menggunakan BERT. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (238kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (368kB)
[thumbnail of Chapter1] Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (389kB)
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (686kB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (510kB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (339kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (334kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)

Abstract

Media sosial TikTok telah menjadi platform utama bagi masyarakat untuk menyuarakan opini terkait berbagai isu, termasuk visi strategis Indonesia Emas 2045 yaitu proyeksi pembangunan nasional menjelang satu abad kemerdekaan Indonesia. Penelitian ini BERTujuan untuk membangun model analisis sentimen terhadap komentar berbahasa Indonesia menggunakan model pre-trained IndoBERT. Dataset terdiri dari 10.138 komentar yang diambil dari 20 konten terpopuler dengan tagar #IndonesiaEmas2045 dalam periode 31 Mei 2023 hingga 31 Maret 2025. Dataset dikategorikan menjadi tiga kelas sentimen yaitu positif sebanyak 3.274 komentar, netral sebanyak 3.515 komentar, dan negatif sebanyak 3.349 komentar. Dataset melalui tahapan preprocessing, pelabelan, pelatihan, validasi, dan pengujian. Model yang telah dilatih diunggah ke Hugging Face dengan nama Indonesia-Emas-2045-Sentiment-Classification. Hasil pengujian menunjukkan performa yang sangat baik dengan akurasi, presisi, recall, dan f1-score masing-masing sebesar 96,5%. Temuan ini menunjukkan bahwa model yang dikembangkan mampu menganalisis sentimen komentar secara akurat dan dapat digunakan dalam memahami opini publik terkait isu Indonesia Emas 2045 di media sosial. / TikTok has become a major platform for the public to express opinions on various issues, including the strategic vision of Indonesia Emas 2045, which is a national development projection approaching the centenary of Indonesia’s independence. This study aims to develop a sentiment analysis model for Indonesian language comments using the pre-trained IndoBERT model. The dataset consists of 10,138 comments collected from the top twenty TikTok contents using the hashtag #IndonesiaEmas2045 during the period from 31 May 2023 to 31 March 2025. The dataset is categorized into three sentiment classes which are 3,274 positive comments, 3,515 neutral comments, and 3,349 negative comments. The data went through preprocessing, labeling, training, validation, and testing stages. The trained model was uploaded to Hugging Face under the name Indonesia-Emas-2045-Sentiment-Classification. The evaluation results show excellent performance with accuracy, precision, recall, and f1-score all reaching 96.5%. These findings demonstrate that the developed model is highly accurate in analyzing comment sentiments and can be effectively used to understand public opinion regarding the Indonesia Emas 2045 issue on social media.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Chen, Excel
NIM03082200002
chennexcel@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Romindo, Romindo
NIDN0111119101
romindo@uph.edu
Uncontrolled Keywords: TikTok; komentar; analisis sentimen; IndoBERT
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Depositing User: Excel Excel
Date Deposited: 11 Aug 2025 02:12
Last Modified: 11 Aug 2025 02:12
URI: http://repository.uph.edu/id/eprint/70051

Actions (login required)

View Item
View Item