Analyzing Digital Addiction through Feature Selection and Machine Learning Techniques

Background/purpose. Digital addiction has become an increasing concern, particularly among students, as excessive engagement with digital platforms negatively impacts academic performance, social interactions, and mental health. This study primarily aims to evaluate and compare the effectiveness of various machine learning and deep learning models in predicting digital addiction. While we examine key features that contribute to classification performance, our focus is not on discovering new predictors but on selecting features that enhance model accuracy. However, few datasets are publicly available, and, moreover, these datasets do not employ similar feature types. As a result, it is not readily clear which set of features a researcher should consider to obtain the most accurate prediction.

Materials/methods. We utilized two publicly available datasets and conducted feature selection using ANOVA scores and Random Forest. We then performed prediction of digital addiction using four machine learning (ML) models—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), and Gradient Boosting (GB)—as well as one deep learning model, Artificial Neural Network (ANN). These models were evaluated using standard performance metrics, including accuracy, precision, recall, and F1 Score.

Results. Our results show that Random Forest, when used to identify the most important feature, performs better overall, especially for models such as KNN. The Random Forest and Gradient Boosting models achieved perfect scores (100% accuracy, precision, recall, and F1-score) on one dataset, and the ANN model reached up to 99.5% accuracy.

Conclusion. Random Forest-based feature importance is particularly effective, and the overall results suggest that ensemble models such as RF and GB are highly reliable. This research will guide future researchers, as they create their own dataset, on the importance of selecting appropriate features in combination with machine learning algorithms to achieve better predictive accuracy. These insights may support early interventions in educational settings to reduce the academic risks associated with digital addiction.

Keywords: Digital Addiction, Student Academic Performance, Sustainable Development Education, Machine Learning, Public Health

References

Abbas, J., Aqeel, M., Abbas, J., Shaher, B., Jaffar, A., Sundas, J., & Zhang, W. (2019). The moderating role of social support for marital adjustment, depression, anxiety, and stress: Evidence from Pakistani working and nonworking women. Journal of Affective Disorders, 244, 231–238. https://doi.org/10.1016/j.jad.2018.07.071

Acharya, S., Adhikari, L., Khadka, S., Paudel, S., & Kaphle, M. (2023). Internet Addiction and Its Associated Factors among Undergraduate Students in Kathmandu, Nepal. Journal of Addiction, 2023. https://doi.org/10.1155/2023/8782527

Ahamed, A. T. M. S., Mahmood, N. T., & Rahman, R. M. (2017). An intelligent system to predict academic performance based on different factors during adolescence. Journal of Information and Telecommunication, 1(2), 155–175. https://doi.org/10.1080/24751839.2017.1323488

Ahmed, M. S., Rony, R. J., Hadi, M. A., Hossain, E., & Ahmed, N. (2023). A Minimalistic Approach to Predict and Understand the Relation of App Usage with Students’ Academic Performance. Proceedings of the ACM on Human-Computer Interaction, 7(MHCI), 1–28. https://doi.org/10.1145/3604240

Al-Alawi, L., Al Shaqsi, J., Tarhini, A., & Al-Busaidi, A. S. (2023). Using machine learning to predict factors affecting academic performance: the case of college students on academic probation. Education and Information Technologies, 28(10), 12407–12432. https://doi.org/10.1007/s10639-023-11700-0

Al-Mamun, F., Hasan, M. E., Mostofa, N. B., Akther, M., Mashruba, T., Arif, M., Chaahat, A. H., Salam, A. B., Akter, M., Abedin, M. A. A., Bulbul, M. I. A., Adnan, M. S., Islam, M. S., Ahmed, M. S., Shahin, M. S. M., Islam, S., Hussain, M. M., Al Habib, A., ALmerab, M. M., … Mamun, M. A. (2024). Prevalence and factors associated with digital addiction among students taking university entrance tests: a GIS-based study. BMC Psychiatry, 24(1), 322. https://doi.org/10.1186/s12888-024-05737-9

Alwagait, E., Shahzad, B., & Alim, S. (2015a). Impact of social media usage on students' academic performance in Saudi Arabia. Computers in Human Behavior, 51, 1092–1097. https://doi.org/https://doi.org/10.1016/j.chb.2014.09.028

Alwagait, E., Shahzad, B., & Alim, S. (2015b). Impact of social media usage on students' academic performance in Saudi Arabia. Computers in Human Behavior, 51, 1092–1097. https://doi.org/https://doi.org/10.1016/j.chb.2014.09.028

Aqeel, M., Rehna, T., Shuja, K. H., & Abbas, J. (2022). Comparison of students’ mental wellbeing, anxiety, depression, and quality of life during COVID-19’s full and partial (smart) lockdowns: a follow-up study at a 5-month interval. Frontiers in Psychiatry, 13, 835585. https://doi.org/10.3389/fpsyt.2022.835585

Balhara, Y. P. S., Mahapatra, A., Sharma, P., & Bhargava, R. (2018). Problematic internet use among students in South-East Asia: Current state of evidence. Indian Journal of Public Health, 62(3), 197–210. https://doi.org/10.4103/ijph.ijph_288_17

Balta, S., Emirtekin, E., Kircaburun, K., & Griffiths, M. D. (2020). Neuroticism, trait fear of missing out, and phubbing: The mediating role of state fear of missing out and problematic Instagram use. International Journal of Mental Health and Addiction, 18, 628–639. https://doi.org/10.1007/s11469-018-9959-8

Chen, X., Zou, D., & Xie, H. (2020). Fifty years of British Journal of Educational Technology: A topic modeling based bibliometric perspective. British Journal of Educational Technology, 51(3), 692–708. https://doi.org/10.1111/bjet.12907

Chia, D. X. Y., Ng, C. W. L., Kandasami, G., Seow, M. Y. L., Choo, C. C., Chew, P. K. H., Lee, C., & Zhang, M. W. B. (2020). Prevalence of internet addiction and gaming disorders in Southeast Asia: A meta-analysis. International Journal of Environmental Research and Public Health, 17(7), 2582. https://doi.org/10.3390/ijerph17072582

Dhanusia, S., Santhana Lakshmi, S., Kumar, A., Prabhu, R., Srinivasan, V., Suganthirababu, P., Kumar, P., Kumaresan, A., Vishnuram, S., Alagesan, J., & Vasanthi, R. K. (2024). Impact of mobile phone usage on dynamic postural control among South Indian college students. Work, 78(2), 441–446. https://doi.org/10.3233/WOR-230161/ASSET/046CC4A7-79A5-43C9-AD51-4328DFB6AFAB/ASSETS/GRAPHIC/10.3233_WOR-230161-FIG3.JPG

Donnelly, E., & Kuss, D. J. (2016). Depression among users of social networking sites (SNSs): The role of SNS addiction and increased usage. Journal of Addiction and Preventive Medicine, 1(2), 107. https://doi.org/10.19104/japm.2016.107

Dresp-Langley, B., & Hutt, A. (2022). Digital addiction and sleep. International Journal of Environmental Research and Public Health, 19(11), 6910. https://doi.org/10.3390/ijerph19116910

Ferdous, A., & Huda, Z. (2023). Social media, new cultures, and new threats: impact on university students in Bangladesh. Human Behavior and Emerging Technologies, 2023. https://doi.org/10.1155/2023/2205861

Giunchiglia, F., Zeni, M., Gobbi, E., Bignotti, E., & Bison, I. (2018). Mobile social media usage and academic performance. Computers in Human Behavior, 82, 177–185. https://doi.org/10.1016/j.chb.2017.12.041

Kuss, D., Griffiths, M., Karila, L., & Billieux, J. (2014). Internet addiction: A systematic review of epidemiological research for the last decade. Current Pharmaceutical Design, 20(25), 4026–4052. https://doi.org/10.2174/13816128113199990617

Jahan, I., Hosen, I., Al Mamun, F., Kaggwa, M. M., Griffiths, M. D., & Mamun, M. A. (2021). How has the COVID-19 pandemic impacted internet use behaviors and facilitated problematic internet use? A Bangladeshi study. Psychology Research and Behavior Management, 1127–1138. https://doi.org/10.2147/prbm.s323570

Junco, R., Heiberger, G., & Loken, E. (2011). The effect of Twitter on college student engagement and grades. Journal of Computer Assisted Learning, 27(2), 119–132. https://doi.org/10.1111/j.1365-2729.2010.00387.x

Karakose, T., Demirkol, M., Yirci, R., Polat, H., Ozdemir, T. Y., & Tülübaş, T. (2023). A conversation with ChatGPT about digital leadership and technology integration: Comparative analysis based on human–AI collaboration. Administrative Sciences, 13(7), 157. https://doi.org/10.3390/admsci13070157

Karakose, T., & Tülübaş, T. (2023). Digital leadership and sustainable school improvement—A conceptual analysis and implications for future Research. Educ. Process Int. J, 12(1), 10–22521. https://doi.org/10.22521/edupij.2023.121.1

Khazaie, H., Lebni, J. Y., Abbas, J., Mahaki, B., Chaboksavar, F., Kianipour, N., Toghroli, R., & Ziapour, A. (2023). Internet addiction status and related factors among medical students: a cross-sectional study in Western Iran. Community Health Equity Research & Policy, 43(4), 347–356. https://doi.org/10.1177/0272684x211025438

Kitsantas, A., Dabbagh, N., Chirinos, D. S., & Fake, H. (2016). College students’ perceptions of positive and negative effects of social networking. Social Networking and Education: Global Perspectives, 225–238. https://doi.org/10.1007/978-3-319-17716-8_14

Leventhal, A. M., Cho, J., Keyes, K. M., Zink, J., Riehm, K. E., Zhang, Y., & Ketema, E. (2021). Digital media use and suicidal behavior in US adolescents, 2009–2017. Preventive Medicine Reports, 23, 101497. https://doi.org/10.1016/j.pmedr.2021.101497

Marciano, L., Ostroumova, M., Schulz, P. J., & Camerini, A.-L. (2022). Digital media use and adolescents’ mental health during the COVID-19 pandemic: a systematic review and meta-analysis. Frontiers in Public Health, 9, 793868. https://doi.org/10.3389/fpubh.2021.793868

Masrom, M., Busalim, A., Griffiths, M. D., Asadi, S., & Mohd Ali, R. (2023). The impact of excessive Instagram use on students’ academic study: a two-stage SEM and artificial neural network approach. Interactive Learning Environments, 1–20. https://doi.org/10.1080/10494820.2023.2184393

Masrom, M., Busalim, A., Griffiths, M. D., Asadi, S., & Mohd Ali, R. (2024). The impact of excessive Instagram use on students’ academic study: a two-stage SEM and artificial neural network approach. Interactive Learning Environments, 32(7), 3546–3565. https://doi.org/10.1080/10494820.2023.2184393

Mazman, S. G., & Usluel, Y. K. (2010). Modeling educational usage of Facebook. Computers & Education, 55(2), 444–453. https://doi.org/10.1016/j.compedu.2010.02.008

Mehta, A. M., & Handriana, T. (2024). Analyzing CSR and customer engagement through green banking digitalization: with the mediating effect of perceived environmental value and moderation effect of customer’s eco-consciousness. Cogent Business & Management, 11(1). https://doi.org/10.1080/23311975.2024.2332502

Meng, S.-Q., Cheng, J.-L., Li, Y.-Y., Yang, X.-Q., Zheng, J.-W., Chang, X.-W., Shi, Y., Chen, Y., Lu, L., Sun, Y., Bao, Y.-P., & Shi, J. (2022). Global prevalence of digital addiction in general population: A systematic review and meta-analysis. Clinical Psychology Review, 92, 102128.

Mirabolghasemi, M., Iahad, N. A., & Rahim, N. Z. A. (2016). Students’ perception towards the potential and barriers of social network sites in higher education. Social Networking and Education: Global Perspectives, 41–49. https://doi.org/10.1007/978-3-319-17716-8_3

Mosharrafa, R. A., Akther, T., & Siddique, F. K. (2024). Impact of social media usage on academic performance of university students: Mediating role of mental health under a cross-sectional study in Bangladesh. Health Science Reports, 7(1), e1788. https://doi.org/10.1002/hsr2.1788

Mukta, M. S. H., Islam, S., Shatabda, S., Ali, M. E., & Zaman, A. (2022). Predicting academic performance: Analysis of students’ mental health condition from social media interactions. Behavioral Sciences, 12(4), 87. https://doi.org/10.3390/bs12040087

Patil, M. (2025). Digital Addiction Dataset. https://github.com/data-manavpatil/DigitalAddiction/blob/main/dataset.csv

Pelima, L. R., Sukmana, Y., & Rosmansyah, Y. (2024). Predicting University Student Graduation Using Academic Performance and Machine Learning: A Systematic Literature Review. IEEE Access. https://doi.org/10.1109/access.2024.3361479

pk673. (2025). Social Media Addiction Analysis - Class Survey Dataset. https://github.com/pk673/Social-Media-Addiction-Analysis/blob/main/ClassSurvey.csv

Prakash, P., Bhanu, S., & Bigul, S. D. (2023). Random forest and logistic regression algorithms: A comparison of their performance. AIP Conference Proceedings, 2548(1). https://doi.org/10.1063/5.0118420

Rahman, M., Roy, P. P., Ali, M., Gonçalves, T., & Sarwar, H. (2023). Software Effort Estimation using Machine Learning Technique. International Journal of Advanced Computer Science and Applications, 14(4), 822–827. https://doi.org/10.14569/IJACSA.2023.0140491

Rahman, M., Sarwar, H., Kader, A., Goncalves, T., & Tin, T. T. (2024). Review and Empirical Analysis of Machine Learning-Based Software Effort Estimation. IEEE Access, 12, 85661–85680. https://doi.org/10.1109/ACCESS.2024.3404879

Rodríguez-Hernández, C. F., Musso, M., Kyndt, E., & Cascallar, E. (2021). Artificial neural networks in academic performance prediction: Systematic implementation and predictor evaluation. Computers and Education: Artificial Intelligence, 2, 100018. https://doi.org/10.1016/j.caeai.2021.100018

Roy, A., & Chakraborty, S. (2023). Support vector machine in structural reliability analysis: A review. Reliability Engineering & System Safety, 109126. https://doi.org/10.1016/j.ress.2023.109126

Rumpf, H.-J., Achab, S., Billieux, J., Bowden-Jones, H., Carragher, N., Demetrovics, Z., Higuchi, S., King, D. L., Mann, K., Potenza, M., Saunders, J. B., Abbott, M., Ambekar, A., Aricak, O. T., Assanangkornchai, S., Bahar, N., Borges, G., Brand, M., Chan, E. M.-L., … Poznyak, V. (2018). Including gaming disorder in the ICD-11: The need to do so from a clinical and public health perspective: Commentary on: A weak scientific basis for gaming disorder: Let us err on the side of caution (van Rooij et al., 2018). Journal of Behavioral Addictions, 7(3), 556–561. https://doi.org/10.1556/2006.7.2018.59

Ryan, P. (2018). Technology: The new addiction. US Naval Institute Publications. Proceedings, 144, 387.

Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2(3), 160. https://doi.org/10.1007/s42979-021-00592-x

Seema, R., & Varik-Maasik, E. (2023). Students’ digital addiction and learning difficulties: shortcomings of surveys in inclusion. Frontiers in Education, 8, 1191817. https://doi.org/10.3389/feduc.2023.1191817

Smith, A., & Anderson, M. (2018). Social Media Use in 2018. https://www.pewresearch.org/internet/2018/03/01/social-media-use-in-2018/

Tin, T. T., Tiung, L. K., Hong, O. J., Hui, C. J., Shen, C. J., Jian, T. Y., & Ikumapayi, O. M. (2024). Does Different Social Media Platforms Lead to Depression, Anxiety, Stress and Bipolar Disorder? A Cross-Sectional Analysis on Private University. Pakistan Journal of Life and Social Sciences (PJLSS), 22(2). https://doi.org/10.57239/PJLSS-2024-22.2.00152

Tower, M., Latimer, S., & Hewitt, J. (2014). Social networking as a learning tool: Nursing students’ perception of efficacy. Nurse Education Today, 34(6), 1012–1017. https://doi.org/10.1016/j.nedt.2013.11.006

Xu, X., Wang, J., Peng, H., & Wu, R. (2019). Prediction of academic performance associated with internet usage behaviors using machine learning algorithms. Computers in Human Behavior, 98, 166–173. https://doi.org/10.1016/j.chb.2019.04.015

Announcement

EDUPIJ Citation Metrics

EDUPIJ News!