An optimized kernel SVM framework for game review sentiment analysis using particle swarm optimization

Ichwanul Muslim Karo Karo; Sri Dewi; Alvi Sahrin Nasution

doi:10.30736/jti.v11i1.1633

Authors

Ichwanul Muslim Karo Karo Universitas Negeri Medan https://orcid.org/0000-0002-2824-5654
Sri Dewi Universitas Negeri Medan
Alvi Sahrin Nasution Universitas Negeri Medan

DOI:

https://doi.org/10.30736/jti.v11i1.1633

Keywords:

SVM, PSO, PUBG, Kernel, Sentiment analysis

Abstract

The digital game industry’s rapid growth has increased interaction between developers and players through online review platforms. These reviews contain vital information about gaming experiences and satisfaction, serving as guides for future game versioning. Sentiment analysis provides a strategic approach to automatically classify reviews, offering data-driven insights for developers. This study focuses on enhancing sentiment analysis performance for Player Unknown's Battlegrounds (PUBG) reviews by integrating Kernel Support Vector Machine (SVM) with Particle Swarm Optimization (PSO). A dataset of 1,205 reviews from the Google Play Store was analyzed using TF-IDF feature extraction and 5-fold cross-validation. While default Kernel SVM achieved 76.78% accuracy, it suffered from low precision (56.9%). Implementing PSO for parameter optimization significantly improved performance, reaching 86.42% accuracy, 70.98% precision, and an 83.03% F1-score. Comparisons with Naïve Bayes, basic SVM, BERT, and Lexicon + SVM confirm that the Kernel SVM + PSO model provides superior and more stable performance. These findings highlight PSO’s effectiveness in SVM parameter tuning. Future research should investigate combining metaheuristic optimization with deep learning models to improve model generalization.

Downloads

Download data is not yet available.

References

[1] R. Narwal and H. Aggarwal, “Predicting Online Game-Addicted Behaviour with Sentiment Analysis Using Twitter Data,” 2022, pp. 505–517. doi: 10.1007/978-981-16-2354-7_45.

[2] S. Fahmi, L. Purnamawati, G. F. Shidik, M. Muljono, and A. Z. Fanani, “Sentiment Analysis of Student Review in Learning Management System Based on Sastrawi Stemmer and SVM-PSO,” in 2020 International Seminar on Application for Technology of Information and Communication (iSemantic), IEEE, Sep. 2020, pp. 643–648. doi: 10.1109/iSemantic50169.2020.9234291.

[3] R. Kashef, “A boosted SVM classifier trained by incremental learning and decremental unlearning approach,” Expert Syst. Appl., vol. 167, p. 114154, Apr. 2021, doi: 10.1016/j.eswa.2020.114154.

[4] A. P. Gopi, R. N. S. Jyothi, V. L. Narayana, and K. S. Sandeep, “Classification of tweets data based on polarity using improved RBF kernel of SVM,” International Journal of Information Technology, vol. 15, no. 2, pp. 965–980, Feb. 2023, doi: 10.1007/s41870-019-00409-4.

[5] A. Mansyur et al., “ Impact of Cosine Similarity Function on SVM Algorithm for Public Opinion Mining About National Sports Week 2024 on X,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 11, no. 3, pp. 263–275, May 2025.

[6] Husni, Arif Muntasa, and Mochamad Dani Hartanto, “Classification of Public Opinion on Online Learning Policies using Various Support Vector Machine’s Kernel,” Technium: Romanian Journal of Applied Sciences and Technology, vol. 17, pp. 427–434, Nov. 2023, doi: 10.47577/technium.v17i.10119.

[7] P. H. Prastyo, I. Ardiyanto, and R. Hidayat, “Indonesian Sentiment Analysis: An Experimental Study of Four Kernel Functions on SVM Algorithm with TF-IDF,” in 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), IEEE, Oct. 2020, pp. 1–6. doi: 10.1109/ICDABI51230.2020.9325685.

[8] N. Mohd Hatta, Z. Ali Shah, and S. Kasim, “Evaluate the Performance of SVM Kernel Functions for Multiclass Cancer Classification,” International Journal of Data Science, vol. 1, no. 1, pp. 37–41, May 2020, doi: 10.18517/ijods.1.1.37-41.2020.

[9] Z. Gao, R. Xia, and P. Zhang, “Prediction of Anti-proliferation Effect of [1,2,3]Triazolo[4,5-<i>d</i>]pyrimidine Derivatives by Random Forest and Mix-Kernel Function SVM with PSO,” Chem. Pharm. Bull. (Tokyo)., vol. 70, no. 10, pp. c22-00376, Oct. 2022, doi: 10.1248/cpb.c22-00376.

[10] H. Prasetya, Z. Situmorang, and R. Rosnelly, “SVM Optimization with Kernel Function for Sentiment Analysis on Social Media twitter (X) in AFC U23 Asian Cup Case Study,” Proceeding of International Conference on Science and Technology UISU, pp. 227–233, Dec. 2024, doi: 10.30743/wjxmmr59.

[11] P. S. Ramesh, S. Surendran, S. Kerthy, R. B, U. G, and S. K. Jain, “Analysis of Text Emotional Tendency and Prediction of Internet Public Opinion Trend Based on Support Vector Machine Algorithm,” in 2023 Second International Conference On Smart Technologies For Smart Nation (SmartTechCon), IEEE, Aug. 2023, pp. 399–404. doi: 10.1109/SmartTechCon57526.2023.10391708.

[12] A. H. Ali and M. Z. Abdullah, “An efficient model for data classification based on SVM grid parameter optimization and PSO feature weight selection,” International Journal of Integrated Engineering, vol. 12, no. 1, pp. 1–12, 2020, doi: 10.30880/ijie.2020.12.01.001.

[13] I. M. Karo Karo, M. F. Md Fudzee, S. Kasim, and A. A. Ramli, “Karonese Sentiment Analysis: A New Dataset and Preliminary Result,” JOIV : International Journal on Informatics Visualization, vol. 6, no. 2–2, p. 523, Aug. 2022, doi: 10.30630/joiv.6.2-2.1119.

[14] I. M. K. Karo, A. Perdana, and S. Dewi, “Automatic Text Review Summarization of Digital Library System Application using TextRank Algorithm and TF-IDF,” in 2024 4th International Conference of Science and Information Technology in Smart Administration (ICSINTESA), IEEE, Jul. 2024, pp. 570–575. doi: 10.1109/ICSINTESA62455.2024.10747952.

[15] A. Toleu, G. Tolegen, and A. Makazhanov, “Character-based Deep Learning Models for Token and Sentence Segmentation,” 2017, Kazan, Tatarstan.

[16] D. Singh and B. Singh, “Investigating the impact of data normalization on classification performance,” Appl. Soft Comput., vol. 97, p. 105524, Dec. 2020, doi: 10.1016/j.asoc.2019.105524.

[17] Arif Bijaksana Putra Negara, “The Influence Of Applying Stopword Removal And Smote On Indonesian Sentiment Classification,” Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, vol. 14, no. 03, pp. 172–185, Oct. 2025, doi: 10.24843/LKJITI.2023.v14.i03.p05.

[18] I. M. Karo Karo, M. F. Md Fudzee, S. Kasim, and A. A. Ramli, “Sentiment Analysis in Karonese Tweet using Machine Learning,” Indonesian Journal of Electrical Engineering and Informatics (IJEEI), vol. 10, no. 1, Mar. 2022, doi: 10.52549/ijeei.v10i1.3565.

[19] A. P. Wibawa, F. A. Dwiyanto, I. A. E. Zaeni, R. K. Nurrohman, and A. Afandi, “Stemming javanese affix words using nazief and adriani modifications,” Jurnal Informatika, vol. 14, no. 1, p. 36, Jan. 2020, doi: 10.26555/jifo.v14i1.a17106.

[20] P. Kiran Kumar, N. Jahna Tejaswi, M. L. Vasanthi, L. L. Srihitha, and B. Phanindra Kumar, “Sentimental Analysis on Multi-domain Sentiment Dataset Using SVM and Naive Bayes Algorithm,” 2022, pp. 201–213. doi: 10.1007/978-3-030-95502-1_16.

[21] C. B. Pande et al., “Comparative Assessment of Improved SVM Method under Different Kernel Functions for Predicting Multi-scale Drought Index,” Water Resources Management, vol. 37, no. 3, pp. 1367–1399, Feb. 2023, doi: 10.1007/s11269-023-03440-0.

[22] Y. Li, J. Lou, X. Tan, Y. Xu, J. Zhang, and Z. Jing, “Adaptive Kernel Learning Kalman Filtering With Application to Model-Free Maneuvering Target Tracking,” IEEE Access, vol. 10, pp. 78088–78101, 2022, doi: 10.1109/ACCESS.2022.3193101.

[23] D. Valero-Carreras, J. Alcaraz, and M. Landete, “Comparing two SVM models through different metrics based on the confusion matrix,” Comput. Oper. Res., vol. 152, p. 106131, Apr. 2023, doi: 10.1016/j.cor.2022.106131.

[24] M. A. P. Putri, N. Y. Setiawan, and B. T. Hanggara, “Analisis Sentimen Ulasan Pengguna Aplikasi PUBG Mobile Menggunakan Karakteristik Quality in Use: Effectiveness and Satisfaction,” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 9, no. 10, pp. 2548–964, Oct. 2025, [Online]. Available: http://j-ptiik.ub.ac.id

[25] Handrizal, F. Y. Manik, and H. A. Misbah, “Sentiment Analysis Based On Pubgm Player Aspects From App Store Reviews Using Bidirectional Encoder Representation From Transformer (BERT),” J. Theor. Appl. Inf. Technol., vol. 102, 2024.

[26] P. R. Sari, D. R. Indah, E. Rasywir, M. A. Firdaus, and G. Athalina, “Comparison of Naive Bayes and SVM Algorithms for Sentiment Analysis of PUBG Mobile on Google Play Store,” SISTEMASI, vol. 13, no. 6, p. 2767, Nov. 2024, doi: 10.32520/stmsi.v13i6.4814.