Analisis Sentimen Ulasan Pengguna Aplikasi Pospay Menggunakan Model Transformer Berbasis Indobert

Putri, Safira Rahmalia (2026) Analisis Sentimen Ulasan Pengguna Aplikasi Pospay Menggunakan Model Transformer Berbasis Indobert. Project Report (Praktek Kerja Lapang dan Magang). Fakultas Ilmu Komputer, Surabaya.

[img] Text (cover)
22083010073.-cover.pdf

Download (1MB)
[img] Text (BAB1)
22083010073-bab1.pdf

Download (272kB)
[img] Text (BAB2)
22083010073-bab2.pdf
Restricted to Repository staff only until 15 September 2028.

Download (553kB)
[img] Text (BAB3)
22083010073-bab3.pdf
Restricted to Repository staff only until 15 September 2028.

Download (805kB)
[img] Text (BAB4)
22083010073-bab4.pdf
Restricted to Repository staff only until 15 September 2028.

Download (248kB)
[img] Text (DAFTAR PUSTAKA)
22083010073-daftarpustaka.pdf

Download (232kB)
[img] Text (LAMPIRAN)
22083010073-lampiran.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

The Field Work Practice (PKL) was conducted at PT Pos Indonesia (Persero) Krembangan Office in Surabaya from August 4, 2025 to August 29, 2025. The PKL activity aimed to apply academic knowledge in a professional work environment, particularly in data processing and analysis. The focus of the PKL activity was sentiment analysis of user reviews of the PosPay application obtained from the Google Play Store. The reviews were analyzed using a Natural Language Processing (NLP) approach with an IndoBERT-based Transformer model to classify sentiment into negative, neutral, and positive categories. The research stages included data collection, text data cleaning, sentiment labeling, model training, and model performance evaluation. The evaluation results show that the sentiment analysis model achieved an accuracy of 89%. The model performed well in classifying negative and positive sentiments, while the classification of neutral sentiments still had a higher error rate. The results of this analysis are expected to be used as evaluation material for PT Pos Indonesia (Persero) in improving the quality of the PosPay application service.

Item Type: Monograph (Project Report (Praktek Kerja Lapang dan Magang))
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorTrimono, TrimonoNIDN0008099501trimono.stat@upnjatim.ac.id
Subjects: Q Science > QA Mathematics > QA76.6 Computer Programming
T Technology > T Technology (General)
Divisions: Faculty of Computer Science > Departemen of Data Science
Depositing User: Safira Rahmalia Putri
Date Deposited: 16 Sep 2026 06:26
Last Modified: 16 Sep 2026 08:54
URI: https://repository.upnjatim.ac.id/id/eprint/60169

Actions (login required)

View Item View Item