cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fardhoni
Contact Email
awatara.res@gmail.com
Phone
+6282219322077
Journal Mail Official
awatara.res@gmail.com
Editorial Address
Jl. DR. Cipto Mangunkusumo No. 29, Kesambi, Kec. Kesambi, Kota Cirebon, Jawa Barat 45132
Location
Kota cirebon,
Jawa barat
INDONESIA
TECHNOVATAR
Published by Awatara Publisher
ISSN : -     EISSN : 30258874     DOI : https://doi.org/10.61434/technovatar.v2i1
Core Subject : Science, Education, Engineering,
Computer Science & IT Control & Systems Engineering Engineering Industrial & Manufacturing Engineering Mathematics
TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi adalah sebuah jurnal ilmiah yang diterbitkan oleh Awatara Publisher dengan fokus utama pada pengkajian mendalam tentang perkembangan teknologi, industri, dan informasi dalam dunia digital. Jurnal ini menyajikan informasi dan pengetahuan terkini yang menginspirasi serta memperluas pemahaman tentang kemajuan teknologi, industri, dan informasi yang memberikan dampak positif bagi perkembangan masyarakat dalam era digital. Jurnal ini terbit secara berkala sebanyak tiga kali dalam setahun pada bulan Januari, April, Juli, dan Oktober.
Arjuna Subject : Ilmu Pengambilan Keputusan (semua kategori) - Sistem Informasi dan Manajemen
Articles 1 Documents
 1 
Search results for , issue "vol 4 no 2 (2026): april" : 1 Documents clear
ANALISIS PERBANDINGAN KINERJA INDOBERT DAN MULTILINGUAL BERT (MBERT) PADA KLASIFIKASI SENTIMEN ULASAN FITUR SHOPEE LIVE DI GOOGLE PLAY STORE Rosmawan, Hendri; Ardiyansyah, Ardiyansyah; Azis, Muhamad Fuad; Rafsyahid, Jaisyi Bagir
TECHNOVATAR Jurnal Teknologi, Industri, dan Informasi Vol 4 No 2 (2026): APRIL
Publisher : Awatara Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61434/technovatar.v4i2.376

Abstract

The Shopee Live streaming e-commerce feature generates a large volume of user reviews on the Google Play Store, yet the text is dominated by informal Indonesian, slang, and code-mixing, making it difficult to analyze using conventional sentiment analysis approaches. This study analyzes and compares the performance of IndoBERT and Multilingual BERT (mBERT) in classifying sentiment of Shopee Live feature reviews into three classes: Positive, Negative, and Neutral. The study follows the CRISP-DM framework, encompassing web scraping of reviews from January-June 2025, filtering, text preprocessing, manual labeling, dataset splitting (80:10:10), fine-tuning both models using HuggingFace Transformers on Google Colaboratory, and evaluation using confusion matrices. The cleaned dataset comprised 5,240 reviews with a class distribution of 44.96% Positive, 35.79% Negative, and 19.25% Neutral. Evaluation results on the test set show that IndoBERT achieved an Accuracy of 89.7%, Precision of 89.5%, Recall of 89.7%, and F1-Score of 89.6%, outperforming mBERT, which achieved an Accuracy of 84.3%, Precision of 84.5%, Recall of 84.3%, and F1-Score of 84.4%. Both models exhibited lower performance on the Neutral class compared to the Positive and Negative classes. These findings confirm that IndoBERT is a more optimal model for sentiment classification of informal Indonesian-language e-commerce reviews, and can be recommended as an AI-based analytical instrument for product development teams to automatically and continuously monitor user sentiment.

Page 1 of 1 | Total Record : 1

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 4 No 4 (2026): OKTOBER Vol 4 No 3 (2026): Juli Vol 4 No 2 (2026): APRIL Vol 4 No 1 (2026): JANUARI Vol 3 No 4 (2025): OKTOBER Vol 3 No 1 (2025): JANUARI Vol 2 No 4 (2024): OKTOBER Vol 2 No 3 (2024): JULI Vol 2 No 2 (2024): APRIL Vol 1 No 1 (2023): OKTOBER