An mRMR-Based Feature Optimization Framework for Gaming Addiction Classification

Rizki Surya Permana; Arif Rahman Hakim; Seshariana Rahma Melati; Muhammad Farhan Maulana

doi:10.25170/jurnalelektro.v19i2.8273

Authors

Rizki Surya Permana Bachelor of Telecommunications Engineering, School of Electrical Engineering, Telkom University, Jakarta 11710, INDONESIA
Arif Rahman Hakim Bachelor of Telecommunications Engineering, School of Electrical Engineering, Telkom University, Jakarta 11710, INDONESIA
Seshariana Rahma Melati Bachelor of Telecommunications Engineering, School of Electrical Engineering, Telkom University, Jakarta 11710, INDONESIA
Muhammad Farhan Maulana Bachelor of Telecommunications Engineering, School of Electrical Engineering, Telkom University, Jakarta 11710, INDONESIA

DOI:

https://doi.org/10.25170/jurnalelektro.v19i2.8273

Keywords:

Feature Selection, Gaming Addiction, Machine Learning, mRMR, Support Vector Machine

Abstract

Gaming addiction classification is challenging because problematic gaming behavior is influenced by multiple behavioral, psychological, lifestyle, and contextual factors, while redundant or weakly informative features may reduce the effectiveness of machine learning models. To address this issue, this study investigates minimum Redundancy Maximum Relevance (mRMR) feature selection to obtain a more compact and discriminative feature representation for gaming addiction classification. Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and K-Nearest Neighbors (KNN) were evaluated using two configurations: a baseline using the complete predictor set and an mRMR-based configuration using the 15 highest-ranked features. All preprocessing, feature selection, hyperparameter tuning, and cross-validation were performed on the training data, while the independent test set was used only for final evaluation. The results show that the effect of mRMR varies across classifiers, indicating that feature reduction does not universally improve classification performance. The strongest improvement was obtained by SVM, whose accuracy increased from 0.940 to 0.960 and F1-score from 0.824 to 0.857 after applying mRMR. The mRMR–SVM model also achieved a precision of 1.000 and a recall of 0.750. In contrast, the baseline XGBoost model achieved a higher recall of 0.914, indicating a trade-off between false-positive reduction and positive-case detection. These findings demonstrate that mRMR can improve classification when the selected feature space is well aligned with the learning mechanism of the classifier, particularly for margin-based SVM. The selected features further indicate that gaming addiction classification is associated not only with gaming intensity but also with psychosocial and lifestyle characteristics. Therefore, the proposed mRMR–SVM configuration provides a compact and effective representation for gaming addiction classification, although validation on larger and more diverse datasets is required before broader generalization.

References

[1] World Health Organization, "Addictive behaviours: Gaming disorder," Oct. 22, 2020. [Online]. Available: https://www.who.int/news-room/questions-and-answers/item/addictive-behaviours-gaming-disorder. [Accessed: Aug. 4, 2026].

[2] World Health Organization, "6C51 Gaming disorder," ICD-11 for Mortality and Morbidity Statistics. [Online]. Available: https://icd.who.int/browse/2025-01/mms/en. [Accessed: Aug. 4, 2026].

[3] J. Billieux, D. J. Stein, J. Castro-Calvo, S. Higuchi, and D. L. King, "Rationale for and usefulness of the inclusion of gaming disorder in the ICD-11," World Psychiatry, vol. 20, no. 2, pp. 198-199, 2021, doi: 10.1002/wps.20848.

[4] A. Musetti, G. Floros, M. Chiappedi, and V. Stavropoulos, "Gaming disorder in the ICD-11: The state of the game," BMC Psychiatry, vol. 25, art. no. 1114, 2025, doi: 10.1186/s12888-025-07576-8.

[5] J. B. Saunders, "Alcohol, drugs and addictive behaviors in ICD-11: Major changes have improved the diagnostic system," European Psychiatry, vol. 68, suppl. 1, p. S11, 2025, doi: 10.1192/j.eurpsy.2025.76.

[6] Q. Wang, K. Mati, and Y. Cai, "The link between problematic internet use, problematic gaming, and psychological distress: Does sleep quality matter?" BMC Psychiatry, vol. 21, art. no. 103, 2021, doi: 10.1186/s12888-021-03105-5.

[7] M. Y. C. Wong, G. F. Yuan, C. Liu, S. K. K. Lam, and H. W. Fung, "The relationship between internet gaming disorder, sleeping quality, self-compassion, physical activity participation and psychological distress: A path analysis," Cambridge Prisms: Global Mental Health, vol. 11, e67, 2024, doi: 10.1017/gmh.2024.36.

[8] T. Alshammari, S. Alseraye, A. Rogowska, N. Alrasheed, and M. Alshammari, "Examining the indirect effect of online gaming on depression via sleep inequality and anxiety-A serial and parallel mediation analysis," Journal of Clinical Medicine, vol. 11, no. 24, art. no. 7293, 2022, doi: 10.3390/jcm11247293.

[9] M. S. Mohamed, G. Rukh, H. B. Schiöth, S. Vadlin, S. Olofsdotter, C. Åslund, and K. W. Nilsson, "Worsened anxiety and loneliness influenced gaming and gambling during the COVID-19 pandemic," Journal of Clinical Medicine, vol. 12, no. 1, art. no. 249, 2023, doi: 10.3390/jcm12010249.

[10] R. Kristensen, S. Pallesen, D. L. King, M. Hysing, and E. K. Erevik, "Problematic gaming and sleep: A systematic review and meta-analysis," Frontiers in Psychiatry, vol. 12, art. no. 675237, 2021, doi: 10.3389/fpsyt.2021.675237.

[11] Y. Yu, V. W. I. Fong, J. H.-Y. Ng, Z. Wang, X. Tian, and J. T. F. Lau, "The associations between loneliness, hopelessness, and self-control and internet gaming disorder among university students who were men who have sex with men: Cross-sectional mediation study," Journal of Medical Internet Research, vol. 25, e43532, 2023, doi: 10.2196/43532.

[12] A. Cudo, N. Kopiś, and A. Zabielska-Mendyk, "Personal distress as a mediator between self-esteem, self-efficacy, loneliness and problematic video gaming in female and male emerging adult gamers," PLOS ONE, vol. 14, no. 12, e0226213, 2019, doi: 10.1371/journal.pone.0226213.

[13] S. Islam, A. N. Tusher, M. S. Mia, and M. S. Rahman, "A machine learning based approach to predict online gaming addiction in the context of Bangladesh," in Proc. 13th Int. Conf. Computing Communication and Networking Technologies (ICCCNT), 2022, pp. 1-7, doi: 10.1109/ICCCNT54827.2022.9984508.

[14] T. Hasan, M. Z. Bonny, R. K. Das, S. Sultana, M. T. Islam, and A. Sattar, "Prediction of Bangladeshi urban children's mental health for the effect of mobile gaming using machine learning," International Journal on Advanced Science, Engineering and Information Technology, vol. 14, no. 3, pp. 859-865, 2024, doi: 10.18517/ijaseit.14.3.18534.

[15] Gülü M, Yagin FH, Gocer I, Yapici H, Ayyildiz E, Clemente FM, Ardigò LP, Zadeh AK, Prieto-González P and Nobari H, “Exploring obesity, physical activity, and digital game addiction levels among adolescents: A study on machine learning-based prediction of digital game addiction,” Front. Psychol. 14:1097145, 2023, doi: 10.3389/fpsyg.2023.1097145

[16] Y. Gan, L. Kuang, X.-M. Xu, M. Ai, J.-L. He, W. Wang, S. Hong, J. Chen, J. Cao, and Q. Zhang, "Application of machine learning in predicting adolescent Internet behavioral addiction," Frontiers in Psychiatry, vol. 15, art. no. 1521051, 2025, doi: 10.3389/fpsyt.2024.1521051.

[17] Liu J, Chen L, Chen Y, Luo J, Yu K, Fan L, Yong C, He H, Liao S, Ge Z and Jiang L, “Explainable machine learning prediction of internet addiction among Chinese primary and middle school children and adolescents: a longitudinal study based on positive youth development data (2019–2022),” Front. Public Health 13:1590689, 2025, doi: 10.3389/fpubh.2025.1590689.

[18] D. Kornev, R. Sadeghian, S. Nwoji, Q. He, A. Gandjbakhche, and S. Aram, "Machine learning-based gaming behavior prediction platform," in Neuroergonomics and Cognitive Engineering, vol. 42, pp. 122-128, 2022, doi: 10.54941/ahfe1001826.

[19] H. Peng, F. Long, and C. Ding, "Feature selection based on mutual information: Criteria of max-dependency, max-relevance, and min-redundancy," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 8, pp. 1226-1238, 2005, doi: 10.1109/TPAMI.2005.159.

[20] C. Ding and H. Peng, "Minimum redundancy feature selection from microarray gene expression data," Journal of Bioinformatics and Computational Biology, vol. 3, no. 2, pp. 185-205, 2005, doi: 10.1142/S0219720005001004.

[21] T. Batbat, A. Güven, M. Altinkaynak, D. Yeşilbaş, E. Uğurgöl, E. Demirci, N. Dolu, and M. İzzetoğlu, "Multimodal neurocognitive assessment of internet gaming disorder using ERP and fNIRS during an oddball paradigm: A machine learning-based classification," Behavioural Brain Research, vol. 507, art. no. 116192, 2026, doi: 10.1016/j.bbr.2026.116192.

[22] L. Wang, L. Zhou, S. Liu, Y. Zheng, Q. Liu, M. Yu, X. Lu, W. Lei, and G. Chen, "Identification of patients with internet gaming disorder via a radiomics-based machine learning model of subcortical structures in high-resolution T1-weighted MRI," Progress in Neuro-Psychopharmacology and Biological Psychiatry, vol. 133, art. no. 111026, 2024, doi: 10.1016/j.pnpbp.2024.111026.

[23] P.-Y. Yeh, C.-L. Lin, C.-K. Sun, and S.-Y. Tung, "Application of EEG-based machine learning in time-frequency and brain connectivity analysis among individuals at high risk of internet gaming disorder with social anxiety," International Journal of Mental Health and Addiction, vol. 24, no. 2, pp. 1841-1864, 2026, doi: 10.1007/s11469-025-01560-9.

[24] J. Y. Lee, M. S. Song, S. Y. Yoo, J. H. Jang, D. Lee, Y. C. Jung, W. Y. Ahn, and J. S. Choi, "Multimodal-based machine learning approach to classify features of internet gaming disorder and alcohol use disorder: A sensor-level and source-level resting-state electroencephalography activity and neuropsychological study," Comprehensive Psychiatry, vol. 130, art. no. 152460, 2024, doi: 10.1016/j.comppsych.2024.152460.

[25] X. Han, L. Wei, Y. Sun, Y. Hu, Y. Wang, W. Ding, Z. Wang, W. Jiang, H. Wang, and Y. Zhou, "MRI-based radiomic machine-learning model may accurately distinguish between subjects with internet gaming disorder and healthy controls," Brain Sciences, vol. 12, no. 1, art. no. 44, 2022, doi: 10.3390/brainsci12010044.

[26] N. T. Thity, A. Rahman, A. Dulmini, M. N. Yasmin, and R. Rois, "An illustration of multi-class ROC analysis for predicting internet addiction among university students," PLOS ONE, vol. 20, no. 7, e0325855, 2025, doi: 10.1371/journal.pone.0325855.

[27] S. Ramírez-Gallego, I. Lastra, D. Martínez-Rego, V. Bolón-Canedo, J. M. Benítez, F. Herrera, and A. Alonso-Betanzos, "Fast-mRMR: Fast minimum redundancy maximum relevance algorithm for high-dimensional big data," International Journal of Intelligent Systems, vol. 32, no. 2, pp. 134-152, 2017, doi: 10.1002/int.21833.

[28] Z. Zhao, R. Anand, and M. Wang, "Maximum relevance and minimum redundancy feature selection methods for a marketing machine learning platform," in Proc. 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2019, pp. 442-452, doi: 10.1109/DSAA.2019.00059.

[29] T. K. Phan, L. Ma, T. N. Nguyen, and S. Do, "BoMGene: Integrating Boruta-mRMR feature selection for enhanced gene expression classification," arXiv preprint, arXiv:2510.00907, 2025, doi: 10.48550/arXiv.2510.00907.