Sentiment Analysis of Shopee App Usage Reviews Using Metaheuristic Algorithm Optimization

yusmanidar; Hendra Cipta; Rini Halila Nasution

doi:10.33541/edumatsains.v10i3.7824

Authors

yusmanidar Universitas Islam Negeri Sumatera Utara
Hendra Cipta State Islamic University of North Sumatra Medan
Rini Halila Nasution State Islamic University of North Sumatra Medan

DOI:

https://doi.org/10.33541/edumatsains.v10i3.7824

Keywords:

Sentiment Analysis;, Particle Swarm Optimization; Support Vector Machine ;, Shopee; Parameter Optimization;

Abstract

Sentiment analysis is widely used to classify opinions expressed in textual data; however, many previous studies employing Support Vector Machine (SVM) do not explicitly address parameter optimization, which can lead to suboptimal classification performance. To address this research gap, this study integrates Particle Swarm Optimization (PSO) to optimize key SVM parameters for sentiment analysis of Shopee application reviews. The dataset consists of 1,000 Indonesian language user reviews collected from the Google Play Store between January and August 2025. Text preprocessing was conducted prior to feature extraction using the Term Frequency–Inverse Document Frequency (TF-IDF) method. PSO was applied to optimize the kernel parameters, penalty parameter (C), and gamma value of the SVM model. The results demonstrate that PSO-based optimization significantly improves classification performance, increasing accuracy from 86.0% to 90.0%, precision from 86.9% to 90.6%, recall from 87.6% to 91.2%, and F1-score from 87.2% to 90.9%. Additionally, positive reviews are dominated by keywords such as “cheap,” “fast,” and “free shipping,” while negative reviews frequently contain terms such as “error” and “slow.” These findings confirm that PSO effectively enhances SVM performance and provides reliable insights into user sentiment toward e-commerce applications.

Author Biographies

Hendra Cipta, State Islamic University of North Sumatra Medan

Department of Mathematics, Faculty of Science and Technology, State Islamic University of North Sumatra Medan, Indonesia

Rini Halila Nasution, State Islamic University of North Sumatra Medan

Department of Mathematics, Faculty of Science and Technology, State Islamic University of North Sumatra Medan

References

Amalia, A., Fathiyya Nuha, S., Zikrinawati, K., & Fahmy, Z. (2023). The influence of brand ambassadors and perceived product quality on purchase intention among Shopee application users. Jurnal Mahasiswa Kreatif, 1(2), 41–52.

Andriana, A. N., Aisha, Z., & Kusuma, A. N. (2021). Training on the use of the Shopee application to increase interest in online business. JMM (Jurnal Masyarakat Mandiri), 5(6), 4–12.

Chen, Y., & Li, Y. (2020). Sentiment analysis of e-commerce product reviews using PSO-optimized support vector machine. Journal of Intelligent Systems, 29(1), 345–358.

Ernawati, S. (2016). Application of particle swarm optimization for feature selection in sentiment analysis of online sales company reviews using Naïve Bayes. Jurnal Teknologi Informasi, 66, 37–39.

Hasto, N. C. (2024). The effect of discounts, brand image, and ease of access on purchase decisions of Shopee application users through purchase intention as an intervening variable. Reslaj: Religion Education Social Laa Roiba Journal, 6(4), 141–143.

Huda, N., Habrizons, F., Satriawan, A., Iranda, M., & Pramuda, T. (2023). Usability testing analysis using the system usability scale (SUS) method on Shopee application user satisfaction. Simkom, 8(2), 208–220.

Idris, I. S. K., Mustofa, Y. A., & Salihi, I. A. (2023). Sentiment analysis of Shopee application usage using support vector machine (SVM). Jambura Journal of Electrical and Electronics Engineering, 5(1), 32–35.

Juwira, R. S. T. (2024). Analysis of Shopee application user satisfaction levels among Generation Z using simple regression. J-ENSISTEC (Journal of Engineering and Sustainable Technology), 10(2), 100–106.

Kumar, A., & Singh, J. P. (2022). Particle swarm optimization-based deep learning model for sentiment analysis on Twitter data. Expert Systems with Applications, 187.

Pangestu, A., Arifin, Y. T., & Safitri, R. A. (2024). Sentiment analysis of public reviews of online games on the Steam platform using Naïve Bayes algorithm. JATI (Jurnal Mahasiswa Teknik Informatika), 7(6), 3106–3113.

Permata, S., & Haryanto, H. (2022). Perlindungan Hukum Terhadap Pengguna Aplikasi Shopee Pay Later. Krisna Law: Jurnal Mahasiswa Fakultas Hukum Universitas Krisnadwipayana, 4(1), 33-47.

Putra, D. A., & Sari, I. N. (2023). Optimasi Parameter Nave Bayes dengan Par ticle Swarm Optimization (PSO) untuk Analisis Sentimen Ulasan Aplikasi Gojek pada Google Play Store. Jurnal Teknologi Informasi dan Ilmu Kom puter (JTIIK), 10(2), 301-310.

Saifurridho, M., Martanto, M., & Hayati, U. (2024). Analisis Algoritma K-Nearest Neighbor terhadap Sentimen Pengguna Aplikasi Shopee. Jurnal Informatika Terpadu, 10(1), 21-26.

Steven, J., & Ramli, A. H. (2023). E-Service Quality, E-Wallet Dan Kepercayaan Terhadap MinatBeli Pada Pengguna PembayaranNonTunai AplikasiShopee. Jurnal Ilmiah Manajemen Kesatuan, 11(2), 267-278.

Utami, H. (2022). Analisis Sentimen dari Aplikasi Shopee Indonesia Menggunakan Metode Recurrent Neural Network. Indonesian Journal of Applied Statistics, 5(1), 31.

Yang, M. Z., & Sihotang, J. I. (2023). Analisis Kepuasan Pengguna Terhadap User Interface Aplikasi E-Commerce Shopee Menggunakan Metode EUCS di Jakarta Barat. Informatics and Digital Expert (INDEX), 4(2), 53-60.