Garuda - Garba Rujukan Digital

Support Vector Machine-Based Sentiment Analysis of Customer Reviews for Android Smartphone Products on Shopee Marketplace Hutauruk, Lucas Namora; Lestari, Sri; Aula, Raisah Fajri
Journal Innovations Computer Science Vol. 4 No. 2 (2025): November
Publisher : Yayasan Kawanad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56347/jics.v4i2.321

The rapid expansion of e-commerce in Indonesia has resulted in a surge of unstructured online reviews, especially on platforms such as Shopee. These reviews offer valuable insights into customer satisfaction, product complaints, and purchasing behavior but remain largely underutilized due to their volume and informal language style. This study applies Support Vector Machine (SVM) with Term Frequency–Inverse Document Frequency (TF-IDF) feature extraction to classify reviews of Android smartphones into positive, negative, and neutral categories. Using a dataset of 300 manually annotated reviews from Samsung, Xiaomi, and Oppo official stores, the model achieved an accuracy of 76.67% and demonstrated stable results through 5-fold cross-validation. The negative class showed the highest performance (F1 = 0.86), while the neutral class performed weakest (F1 = 0.62), reflecting challenges posed by mixed opinions and underrepresented samples. Compared with Naïve Bayes and Logistic Regression, the SVM model consistently outperformed both baselines, confirming its suitability for high-dimensional text data and informal Indonesian expressions. The findings highlight SVM’s potential to support automated sentiment monitoring in e-commerce, enabling businesses to identify emerging issues, improve customer service strategies, and leverage positive reviews for marketing. Future research should consider larger and more balanced datasets, techniques for handling imbalanced classes, and integration with deep learning models such as LSTM or BERT to improve performance and generalization.

Support Vector Machine-Based Sentiment Analysis of Customer Reviews for Android Smartphone Products on Shopee Marketplace Hutauruk, Lucas Namora; Lestari, Sri; Aula, Raisah Fajri
Journal Innovations Computer Science Vol. 4 No. 2 (2025): November
Publisher : Yayasan Kawanad

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56347/jics.v4i2.321

The rapid expansion of e-commerce in Indonesia has resulted in a surge of unstructured online reviews, especially on platforms such as Shopee. These reviews offer valuable insights into customer satisfaction, product complaints, and purchasing behavior but remain largely underutilized due to their volume and informal language style. This study applies Support Vector Machine (SVM) with Term Frequency–Inverse Document Frequency (TF-IDF) feature extraction to classify reviews of Android smartphones into positive, negative, and neutral categories. Using a dataset of 300 manually annotated reviews from Samsung, Xiaomi, and Oppo official stores, the model achieved an accuracy of 76.67% and demonstrated stable results through 5-fold cross-validation. The negative class showed the highest performance (F1 = 0.86), while the neutral class performed weakest (F1 = 0.62), reflecting challenges posed by mixed opinions and underrepresented samples. Compared with Naïve Bayes and Logistic Regression, the SVM model consistently outperformed both baselines, confirming its suitability for high-dimensional text data and informal Indonesian expressions. The findings highlight SVM’s potential to support automated sentiment monitoring in e-commerce, enabling businesses to identify emerging issues, improve customer service strategies, and leverage positive reviews for marketing. Future research should consider larger and more balanced datasets, techniques for handling imbalanced classes, and integration with deep learning models such as LSTM or BERT to improve performance and generalization.

Implementation of the Naive Bayes Method in Looker Studio for data on the achievement of Great IDN in IDN Akhwat School Akbar, Yuma; Az-Zahra, Haura Salsabila; Setiawan, Kiki; Fajri, Raisah
Indonesian Journal of Multidisciplinary Science Vol. 3 No. 11 (2024): Indonesian Journal of Multidisciplinary Science
Publisher : International Journal Labs

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55324/ijoms.v3i11.981

The IDN Hebat program is an important tool for schools to track and analyze student achievement data. However, with the targeted activities in the IDN program, challenges arise in managing and measuring achievement data efficiently. The research aims to develop a Web Cloud-based data management system for IDN Hisbat achievements at IDN Akhwat School by utilizing Google Looker Studio and the Naive Bayes Algorithm. The data source used in this study is by applying a classification dataset obtained from student achievement information data in the Great IDN Program. The results of this analysis show that the highest accuracy of teaching achievement fell on the status of exceeding the target with a percentage of 89%, and the highest class that placed the status above the target was class 9A with an average percentage of 35%. In addition, the results from this analysis can help coordinators and schools in planning more effective and strategic programs in the future. Overall, this study provides important benefits in improving the quality of teaching and student coaching, as well as supporting data-driven decision-making. This study is expected to enhance the efficiency, accuracy, and effectiveness of managing student achievement, while also supporting the attainment of optimal educational goals for each student to achieve extraordinary results.

Implementation of a Chatbot Using the Waterfall Method to Improve Helpdesk Service Efficiency at IT Consulting Companies Lestari, Sri; Aprillia, Eka Putri; Aula, Raisah Fajri
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i3.5207

PT XYZ is a company engaged in information and communication technology services, supporting customers' digital transformation. The effectiveness of helpdesk services plays a crucial role in maintaining operations and fostering customer relationships. However, the issue reporting process is still handled manually through platforms such as WhatsApp and email, causing several problems, including inefficient ticket management, delays in ticket number assignment, and limited historical data. This study developed a chatbot based on Microsoft Copilot Studio to automate ticket creation, supported by Power Apps to address the lack of two-way communication features, aiming to support Customer Relationship Management (CRM) efforts. The system was developed using Waterfall methodology. The results showed significant improvements in service efficiency: the previous average initial response time of 2 days, 19 hours, and 13 minutes was eliminated due to automatic ticket number assignment; the average issue resolution time decreased from 5 days, 6 hours, and 20 minutes to 42 minutes; and ticket history search time improved from 14 minutes to 2 seconds. The chatbot successfully accelerated the reporting process, enhanced data recording, and reduced the workload of the helpdesk team. This solution significantly improved helpdesk efficiency and strengthened customer engagement.

Title

Found 14 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 14 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 14 Documents
Search