RITONGA, YOHANNES ALESANDRO PUTRANTA (2025) ANALISIS SENTIMEN TERHADAP APLIKASI CHAT GPT BERDASARKAN ULASAN PLAYSTORE MENGGUNAKAN INDOBERT. S1 thesis, Universitas Mercu Buana Jakarta - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
41521010199-Yohannes Alesandro Putranta Ritonga-01 Cover - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Download (308kB) |
|
Text (BAB I)
41521010199-Yohannes Alesandro Putranta Ritonga-02 Bab 1 - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (108kB) |
|
Text (BAB II)
41521010199-Yohannes Alesandro Putranta Ritonga-03 Bab 2 - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (62kB) |
|
Text (BAB III)
41521010199-Yohannes Alesandro Putranta Ritonga-04 Bab 3 - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (122kB) |
|
Text (BAB IV)
41521010199-Yohannes Alesandro Putranta Ritonga-05 Bab 4 - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (4MB) |
|
Text (BAB V)
41521010199-Yohannes Alesandro Putranta Ritonga-06 Bab 5 - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (36kB) |
|
Text (DAFTAR PUSTAKA)
41521010199-Yohannes Alesandro Putranta Ritonga-07 Daftar Pustaka - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (101kB) |
|
Text (LAMPIRAN)
41521010199-Yohannes Alesandro Putranta Ritonga-08 Lampiran - YOHANNES ALESANDRO PUTRANTA RITONGA.pdf Restricted to Registered users only Download (486kB) |
Abstract
Penelitian ini bertujuan untuk menganalisis sentimen pengguna terhadap aplikasi ChatGPT berdasarkan ulasan berbahasa Indonesia yang diperoleh dari Google Playstore. Mengingat banyaknya ulasan yang tidak terstruktur dan mencakup berbagai aspek seperti performa, fitur, hingga keamanan, maka diperlukan pendekatan otomatis dan akurat dalam mengklasifikasikan sentimen. Dalam studi ini digunakan model IndoBERT, yaitu model pre-trained berbasis Transformer yang telah disesuaikan untuk Bahasa Indonesia. Dataset yang digunakan terdiri dari 35.140 ulasan yang dikumpulkan sepanjang tahun 2024 dan melalui proses preprocessing serta pelabelan otomatis berdasarkan skor rating. Model IndoBERT kemudian dilatih menggunakan teknik fine-tuning dan dievaluasi menggunakan metrik seperti akurasi, precision, recall, dan F1-score. Hasil menunjukkan akurasi keseluruhan sebesar 95%, dengan performa terbaik pada kelas sentimen positif (F1- score 0.98), sedangkan performa pada kelas netral sangat rendah (F1-score 0.00) akibat ketidakseimbangan jumlah data. Penelitian ini menunjukkan bahwa IndoBERT mampu melakukan klasifikasi sentimen dengan sangat baik pada kelas dominan dan dapat digunakan sebagai alat bantu evaluasi persepsi pengguna terhadap aplikasi. This study aims to analyze user sentiment toward the ChatGPT application based on Indonesian-language reviews collected from the Google Playstore. Given the large volume of unstructured reviews covering aspects such as performance, features, and security, an automated and accurate approach to sentiment classification is required. This study employs IndoBERT, a pre-trained Transformer-based model specifically adapted for the Indonesian language. The dataset consists of 35,140 reviews collected throughout 2024, which underwent preprocessing and automatic labeling based on user rating scores. The IndoBERT model was fine-tuned and evaluated using metrics such as accuracy, precision, recall, and F1-score. The results show an overall accuracy of 95%, with the best performance in the positive sentiment class (F1-score 0.98), while performance in the neutral class was very low (F1-score 0.00) due to class imbalance. This research demonstrates that IndoBERT performs very well on dominant classes and can be used as a tool to evaluate user perception of the application.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41521010199 |
| Uncontrolled Keywords: | Analisis Sentimen, IndoBERT, ChatGPT, Google Playstore, Natural Language Processing. Sentiment Analysis, IndoBERT, ChatGPT, Google Playstore, Natural Language Processing. |
| 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: | Maulana Arif Hidayat |
| Date Deposited: | 04 Sep 2025 03:44 |
| Last Modified: | 04 Sep 2025 03:44 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/97425 |
Actions (login required)
 |
View Item |
