Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Ihtada, Fahrendra Khoirul
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Energy Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Aspect-based Multilabel Classification of E-commerce Reviews using Fine-tuned IndoBERT Ihtada, Fahrendra Khoirul; Alfianita, Rizha; Aziz, Okta Qomaruddin
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 1, February 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i1.2088

Abstract

In recent years, e-commerce has experienced rapid growth. A significant change in consumer behavior is marked by the ease of access and time flexibility offered by e-commerce platforms, as well as the existence of the review feature to assess products and services. However, with the ever-increasing number of reviews, consumers and store owners face challenges in sorting out relevant information. This research focuses on the multilabel classification of Indonesian e-commerce reviews. This research was undertaken because the application of multilabel classification, especially for e-commerce reviews in Indonesia, has received little attention. This research compares three classification models: end-to-end IndoBERT, IndoBERT-CNN, and IndoBERT-LSTM, to determine the most effective model for multilabel aspect classification of customer reviews. The multilabel classification method was applied to determine the aspect categories of the reviews, such as product, customer service, and delivery, using different thresholds for evaluation. Results show that 0.6 threshold is optimal, with the IndoBERT-LSTM model as the best-performing model for the multilabel aspect classification of these e-commerce reviews. Optimal classification of the model enables more precise information extraction from customer reviews. This can be useful for e-commerce businesses to gain insight from the reviews they get from customers. This insight can be used to find out which aspects need to be improved from the e-commerce business which leads to increased customer satisfaction and trust.
E-commerce Product Review Classification using Neural Network-Based Approach Ihtada, Fahrendra Khoirul; Abidin, Zainal; Crysdian, Cahyo
JOIV : International Journal on Informatics Visualization Vol 9, No 6 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.6.2845

Abstract

E-commerce has become an integral part of how people shop, with the rise of customer reviews on various platforms. These reviews provide important insights into product, customer service, and delivery. The growing volume of e-commerce reviews makes manual sorting time-consuming and error-prone for business owners. This study aims to classify e-commerce reviews into three categories: product, customer service, and delivery. The data was collected from e-commerce customer reviews on Tokopedia and labeled using crowdsourcing for ground truth. To classify the reviews, a Neural Network is performed with various numbers of node and learning rate. TF-IDF is also used for feature extraction to capture important features from the review data. From nine test scenarios, model B3 with 50 nodes in the first hidden layer and a learning rate of 0.1 provided the best performance with an accuracy of 65.85%, precision of 62.27%, recall of 58.61%, and f1-score of 59.71%. Validation using K-Fold Cross Validation shows an average accuracy of 64.17% at k=10. Word analysis with TF-IDF identified dominant words in each category. The B3 model is not yet able to classify reviews perfectly, due to the large and unbalanced dataset, less complex model architecture, and less effective TF-IDF preprocessing. However, this study shows potential for better classification in the future. With optimization, this model can be very useful for e-commerce business owners to gain insight from customer reviews and can help them to identify aspects that will lead to customer satisfaction and trust.
Co-Authors Alfianita, Rizha Cahyo Crysdian Okta Qomaruddin Aziz Zainal Abidin