Attention Span Classification of Social Media Users Using Multi-Kernel Support Vector Machine Based on Survey Data

Reza Pahlevi; Darren Lucius; Diasta Natanael Sembiring; Delima Sitanggang

doi:10.61255/decoding.v4i2.1193

Authors

Reza Pahlevi Universitas Prima Indonesia
Darren Lucius Universitas Prima Indonesia
Diasta Natanael Sembiring Universitas Prima Indonesia
Delima Sitanggang Universitas Prima Indonesia

DOI:

https://doi.org/10.61255/decoding.v4i2.1193

Keywords:

Attention span, Machine learning, Mental health, Social media, Support vector machine

Abstract

Purpose – This study aims to examine whether self-reported attention-related difficulty categories among social media users can be classified using a leakage-free machine learning framework. It addresses the risk of inflated performance in survey-based classification by excluding the same items used to construct the target label from the predictor set.
Methods – The study used the public Social Media and Mental Health (SMMH) Kaggle dataset with 478 valid respondents. A three-class label was constructed from Q10, Q12, and Q14 using percentile thresholds (P33 = 9.0; P66 = 12.0), producing High (n = 208), Medium (n = 152), and Low (n = 118) categories. These label-generating items were excluded from predictors. The remaining variables were processed in a scikit-learn Pipeline using MinMax scaling, ordinal encoding, and One-Hot Encoding. Multi-kernel SVM models and five baseline classifiers were evaluated using a stratified 70:30 split, cross-validation, F1 metrics, balanced accuracy, and permutation importance.
Findings – Random Forest achieved the highest performance, with 63.19% accuracy and 62.26% weighted F1. Linear SVM was the best SVM model, achieving 61.81% accuracy, 60.08% weighted F1, 58.99% macro F1, and 59.11% balanced accuracy. The strongest predictors were Restless Without Social Media, Use Without Purpose, and Interest Fluctuation.
Research implications – The findings are preliminary, dataset-specific, and based on a survey-derived composite label whose internal reliability still requires validation.
Originality – This study contributes a leakage-controlled classification approach for analyzing attention-related survey categories.

Abstract views: 22 ,

PDF downloads: 7

Downloads

Download data is not yet available.

References

J. Firth et al., “The ‘online brain’: how the Internet may be changing our cognition,” World Psychiatry, vol. 18, no. 2, hal. 119–129, 2019, doi: 10.1002/wps.20617.

T. Yan, C. Su, W. Xue, Y. Hu, dan H. Zhou, “Mobile phone short video use negatively impacts attention functions: An EEG study,” Front. Psychol., vol. 14, hal. 1106297, 2023, doi: 10.3389/fpsyg.2023.1106297.

M. Shanmugasundaram, M. Tamilarasu, dan S. S. Mohan, “The impact of digital technology, social media, and artificial intelligence on cognitive functions: A review,” Front. Cogn., vol. 2, hal. 1203077, 2023, doi: 10.3389/fcogn.2023.1203077.

V. S. Ramachandran, Ed., Encyclopedia of Human Behavior, 2nd ed., vol. 3. Amsterdam, Netherlands: Elsevier, 2012.

G. Mark, D. Gudith, dan U. Klocke, “The cost of interrupted work: More speed and stress,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Florence, Italy, 2008, hal. 107–110. doi: 10.1145/1357054.1357072.

L. D. Rosen, L. M. Carrier, dan N. A. Cheever, “Facebook and texting made me do it: Media-induced task-switching while studying,” Comput. Human Behav., vol. 29, no. 3, hal. 948–958, 2013, doi: 10.1016/j.chb.2012.12.001.

N. S. Hawi dan M. Samaha, “The relations among social media addiction, self-esteem, and life satisfaction in university students,” Soc. Sci. Comput. Rev., vol. 35, no. 5, hal. 576–586, 2017, doi: 10.1177/0894439316660340.

K. Rioja, S. Cekic, D. Bavelier, dan S. E. Baumgartner, “Unraveling the link between media multitasking and attention across three samples,” J. Commun., vol. 73, no. 5, hal. 427–439, 2023, doi: 10.1093/joc/jqad025.

J. M. Twenge, G. N. Martin, dan W. K. Campbell, “Decreases in psychological well-being among American adolescents after 2012 and links to screen time,” Emotion, vol. 18, no. 6, hal. 765–780, 2018, doi: 10.1037/emo0000403.

J. M. Twenge, “More time on technology, less happiness? Associations between digital media use and psychological well-being,” Curr. Dir. Psychol. Sci., vol. 28, no. 4, hal. 372–379, 2019, doi: 10.1177/0963721419838244.

L. Nguyen, A. T. Nguyen, M. M. McDonald, dan C. M. Burns, “Feeds, Feelings, and Focus: A Systematic Review and Meta-Analysis Examining the Cognitive and Mental Health Correlates of Social Media Use in Adolescents,” Adolescents, vol. 4, no. 1, hal. 58–78, 2024, doi: 10.3390/adolescents4010005.

N. K. Iyortsuun, S.-H. Kim, M. Jhon, H.-J. Yang, dan S. Pant, “A review of machine learning and deep learning approaches on mental health diagnosis,” Healthcare, vol. 11, no. 3, hal. 285, 2023, doi: 10.3390/healthcare11030285.

J. Kim, D. Lee, dan E. Park, “Machine learning for mental health in social media: Bibliometric study,” J. Med. Internet Res., vol. 23, no. 5, hal. e24870, 2021, doi: 10.2196/24870.

C. Cortes dan V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, hal. 273–297, 1995, doi: 10.1007/BF00994018.

B. Schölkopf dan A. J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. Cambridge, MA, USA: MIT Press, 2002.

A. Golchha, M. Kuchibhotla, dan A. Mukherjee, “Mental health classifier using SVM,” in Lecture Notes in Computer Science, vol. 15346, Cham, Switzerland: Springer, 2024, hal. 127–138. doi: 10.1007/978-981-96-0573-6_10.

S. B. Kotsiantis, I. Zaharakis, and P. Pintelas, “Supervised machine learning: A review of classification techniques,” Informatica, vol. 31, no. 3, pp. 249–268, 2007.

A. F. Ward, K. Duke, A. Gneezy, dan M. W. Bos, “Brain Drain: The mere presence of one’s own smartphone reduces available cognitive capacity,” J. Assoc. Consum. Res., vol. 2, no. 2, hal. 140–154, 2017, doi: 10.1086/691462.

T. Haliti-Sylaj dan A. Sadiku, “Impact of short reels on attention span and academic performance of undergraduate students,” Eur. J. Appl. Sci., vol. 11, no. 5, hal. 266–277, 2023, doi: 10.14738/aivp.115.15623.

S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine learning-based science,” Patterns, vol. 4, no. 9, p. 100804, 2023, doi: 10.1016/j.patter.2023.100804.

S. Kaufman, S. Rosset, C. Perlich, and O. Stitelman, “Leakage in data mining: Formulation, detection, and avoidance,” ACM Trans. Knowl. Discov. Data, vol. 6, no. 4, pp. 1–21, 2012, doi: 10.1145/2382577.2382579.

J. C. Nunnally and I. H. Bernstein, Psychometric Theory, 3rd ed. New York, NY, USA: McGraw-Hill, 1994.

D. L. Streiner, “Starting at the beginning: An introduction to coefficient alpha and internal consistency,” J. Pers. Assess., vol. 80, no. 1, pp. 99–103, 2003, doi: 10.1207/S15327752JPA8001_18.

S. Aksoy and R. M. Haralick, “Feature normalization and likelihood-based similarity measures for image retrieval,” Pattern Recognit. Lett., vol. 22, no. 5, pp. 563–582, 2001, doi: 10.1016/S0167-8655(00)00112-4.

F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, hal. 2825–2830, 2011.

L. Buitinck et al., “API design for machine learning software: Experiences from the scikit-learn project,” in Proc. ECML PKDD Workshop: Languages for Data Mining and Machine Learning, 2013, pp. 108–122.

A. Altmann, L. Toloşi, O. Sander, and T. Lengauer, “Permutation importance: A corrected feature importance measure,” Bioinformatics, vol. 26, no. 10, pp. 1340–1347, 2010, doi: 10.1093/bioinformatics/btq134.

A. Fisher, C. Rudin, dan F. Dominici, “All models are wrong, but many are useful,” J. Mach. Learn. Res., vol. 20, no. 177, hal. 1–81, 2019.

T. E. Robinson dan K. C. Berridge, “Incentive-sensitization and addiction,” Addiction, vol. 96, no. 1, hal. 103–114, 2001, doi: 10.1080/09652140020016996.

B. T. Sharpe dan R. A. Spooner, “Dopamine-scrolling: A modern public health challenge requiring urgent attention,” Perspect. Public Health, vol. 144, no. 6, hal. 315–316, 2024, doi: 10.1177/17579139241240564.

C. Montag, B. Lachmann, M. Herrlich, dan K. Zweig, “Addictive features of social media/messenger platforms and freemium games,” Int. J. Environ. Res. Public Health, vol. 16, no. 14, hal. 2612, 2019, doi: 10.3390/ijerph16142612.

A. C. Drody, E. J. Pereira, dan D. Smilek, “A desire for distraction: Uncovering the rates of media multitasking during online research study tasks,” Attention, Perception, Psychophys., vol. 85, no. 7, hal. 2431–2450, 2023, doi: 10.3758/s13414-023-02721-5.

J. Xie, Y. Wang, Z. Lin, dan X. Li, “The effect of short-form video addiction on undergraduates’ academic procrastination: A moderated mediation model,” Front. Psychol., vol. 14, hal. 1028045, 2023, doi: 10.3389/fpsyg.2023.1028045.

M. Wadsley dan N. Ihssen, “The predictive utility of reward-based motives underlying excessive and problematic social networking site use,” Psychol. Addict. Behav., vol. 36, no. 4, hal. 373–382, 2022, doi: 10.1037/adb0000693.

Z. Yang, X. Asbury, dan M. Griffiths, “An investigation of problematic smartphone use among Chinese university students: Associations with academic anxiety, procrastination, self-regulation and subjective wellbeing,” Int. J. Ment. Health Addict., vol. 17, no. 3, hal. 596–614, 2019, doi: 10.1007/s11469-018-9973-8.