Conference Paper2025

Can Augmentation Help Small Survey Datasets: Machine Learning Models for Predicting Academic Impact of Social Media Addiction and Procrastination

Tausia Tahsin Nuzum, Sumita Tasnim, Tasnia Rafique Simran, Nabarun Halder, Ashraful Islam, M Ashraful Amin

2025 IEEE 23rd Student Conference on Research and Development (SCOReD)

IEEE, pp. 1-6

DOI: 10.1109/scored68498.2025.11398912URL

Abstract

Social media use is prevalent among students and is associated with procrastination that can negatively affect academic performance. Detecting at-risk students from small, imbalanced surveys is challenging. This study examines whether synthetic data can improve prediction. Risk prediction was performed using seven classifiers: logistic regression (LR), random forest (RF), gradient boosting (GB), support vector machine (SVM) with RBF kernel, k-nearest neighbors (KNN), Gaussian Naive Bayes (GNB), and a multi-layer perceptron (MLP), on two small student surveys. Data augmentation techniques used are: Synthetic Minority Over-sampling Technique for Nominal and Continuous Features (SMOTENC), Gaussian Copula (GC), and Conditional Tabular Generative Adversarial Network (CTGAN). Without augmentation, SVM, GB, and RF achieved similar accuracy on Dataset-1 (≈0.93). GNB led Dataset-2 (0.907 accuracy), with RF, GB, SVM, and MLP following closely (≈0.89-0.90). Augmentation effects are model and dataset dependent and generally modest with Tree ensembles remaining largely stable. The model with the largest improvement was RF, gaining a +0.013 increase in F1 on GC for Dataset-2. The MLP declined with synthetic data. Hence synthetic augmentation might not be a universal remedy for small-scale datasets. Overall, lightweight models trained on a modest set of smartphone-like features can predict the risk of procrastination affecting academic performance and are suitable for on device use.

Keywords

  • Procrastination
  • academic performance
  • CTGAN
  • social media addiction
  • Gaussian copula
  • SMOTE-NC
  • synthetic data augmentation

CCDS Authors

Nabarun Halder
Nabarun Halder

Nabarun Halder

  • Research Assistant, CCDS

Published at

UbiComp, IJCNN, HCII, IEEE Access

Research Interests

Machine Learning, Deep Learning, Natural Language Processing, Health Informatics, Human-Computer Interaction

Ashraful Islam, PhD
Ashraful Islam

Ashraful Islam, PhD

  • Center Director, CCDS
  • Director, HCI Wing

Assistant Professor

Department of Computer Science and Engineering

Independent University, Bangladesh (IUB)

Published at

CHI, UIST, UbiComp, IJCNN, ICIP, HCII, ICDMW, BLP, IEEE Internet of Things Journal, JMIR, JMIR Human Factors, JMIR Formative Research, IEEE Access, Smart Agricultural Technology, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Human-Computer Interaction, AI for Social Good, AI for Public Health, AI for Impact

Prof. M Ashraful Amin, PhD
M Ashraful Amin, PhD

Prof. M Ashraful Amin, PhD

  • Founder Director, CCDS
  • Director, AI/ML, HCI & DS Wings

Professor

+1 more affiliation

Department of Information Sciences and Technology

George Mason University, USA

Published at

ACL, CHI, UbiComp, ECAI, WACV, PAKDD, IJCNN, ICPR, ICIP, HCII, CLEF, BLP, Scientific Reports, JMIR, IEEE Access, Smart Agricultural Technology, Frontiers in Computational Neuroscience, Diabetes Research and Clinical Practice, PLOS ONE

Research Interests

Machine Learning, Cognitive & Vision Science, Cybernetics, Surveillance & Security, ICT in Education, Health, & Agriculture, Human-Computer Interaction, Internet of Things, Robotics

References

  1. 1.N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357[10.1613/jair.953]
  2. 2.David Thissen, Lynne Steinberg, Daniel Kuang. (2002). Quick and Easy Implementation of the Benjamini-Hochberg Procedure for Controlling the False Positive Rate in Multiple Comparisons. Journal of Educational and Behavioral Statistics, 27(1), 77–83[10.3102/10769986027001077]
  3. 3.Alhassan Mumuni, Fuseini Mumuni. (2022). Data augmentation: A comprehensive survey of modern approaches. Array, 16, 100258[10.1016/j.array.2022.100258]
  4. 4.Piers Steel, Katrin B Klingsieck. (2016). Academic Procrastination: Psychological Antecedents Revisited. Australian Psychologist, 51(1), 36–46[10.1111/ap.12173]
  5. 5.Mimi Mukherjee, Matloob Khushi. (2021). SMOTE-ENC: A Novel SMOTE-Based Method to Generate Synthetic Data for Nominal and Continuous Features. Applied System Innovation, 4(1), 18[10.3390/asi4010018]
  6. 6.Danial Hooshyar, Margus Pedaste, Yeongwook Yang. (2019). Mining Educational Data to Predict Students’ Performance through Procrastination Behavior. Entropy, 22(1), 12[10.3390/e22010012]
  7. 7.Fuschia M. Sirois. (2015). Is procrastination a vulnerability factor for hypertension and cardiovascular disease? Testing an extension of the procrastination–health model. Journal of Behavioral Medicine, 38(3), 578–589[10.1007/s10865-015-9629-2]
  8. 8.Meirav Hen, Marina Goroshit. (2018). The effects of decisional and academic procrastination on students’ feelings toward academic procrastination. Current Psychology, 39(2), 556–563[10.1007/s12144-017-9777-3]
  9. 9.Amy Nowacki. (2017). Chi-square and Fisher’s exact tests. Cleveland Clinic Journal of Medicine, 84(9 suppl 2), e20–e25[10.3949/ccjm.84.s2.04]
  10. 10.Lei Zhao. (2021). Social Media Addiction and Its Impact on College Students' Academic Performance: The Mediating Role of Stress. The Asia-Pacific Education Researcher, 32(1), 81–90[10.1007/s40299-021-00635-0]
  11. 11.Yared Fentaw, Bekalu Tadesse Moges, Sayed M. Ismail. (2022). Academic Procrastination Behavior among Public University Students. Education Research International, 2022, 1–8[10.1155/2022/1277866]
  12. 12.Hamidreza Farhadi Rad, Shima Bordbar, Jamshid Bahmaei, Marjan Vejdani, Ali Reza Yusefi. (2025). Predicting academic procrastination of students based on academic self-efficacy and emotional regulation difficulties. Scientific Reports, 15(1), 3003[10.1038/s41598-025-87664-7]
  13. 13.Christof Imhof, Ioan-Sorin Comsa, Martin Hlosta, Behnam Parsaeifard, Ivan Moser, Per Bergamin. (2022). Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models. IEEE Transactions on Learning Technologies, 16(5), 648–663[10.1109/tlt.2022.3221495]
  14. 14.David Meyer, Thomas Nagler, Robin J. Hogan. (2021). Copula-based synthetic data augmentation for machine-learning emulators. Geoscientific model development, 14(8), 5205–5215[10.5194/gmd-14-5205-2021]
  15. 15.Pedro Machado, Bruno Fernandes, Paulo Novais. (2022). Benchmarking Data Augmentation Techniques for Tabular Data. Lecture notes in computer science, 104–112[10.1007/978-3-031-21753-1_11]
  16. 16.Pu Song, Xiangwei Liu, Xuan Cai, Mengmeng Zhong, Qingqing Wang, Xiangmei Zhu. (2024). Predictive analysis of college students’ academic procrastination behavior based on a decision tree model. Humanities and Social Sciences Communications, 11(1)[10.1057/s41599-024-03300-1]
  17. 17.Valdemar Švábenský, Conrad Borchers, Elizabeth B. Cloude, Atsushi Shimada. (2025). Evaluating the Impact of Data Augmentation on Predictive Model Performance. , 126–136[10.1145/3706468.3706485]
  18. 18.Nisha S. Raj, Renumol V. G.. (2023). An Approach for Early Prediction of Academic Procrastination in e-Learning Environment. International Journal of Information and Education Technology, 13(1), 73–81[10.18178/ijiet.2023.13.1.1782]
  19. 19.Olayiwola Alfa Abdullahi, Mahadi Bahari, Suraya Miskon, Mohamad Haider Abu Yazid. (2024). Social Media Addiction and Academic Performance: A Bibliometric Analysis Approach. International Journal of Academic Research in Business and Social Sciences, 14(1)[10.6007/ijarbss/v14-i1/20536]
  20. 20.J.F. Walde, G. Tappeiner, U. Tappeiner, E. Tasser, H.W. Holub. (2003). Statistical aspects of multilayer perceptrons under data limitations. Computational Statistics & Data Analysis, 46(1), 173–188[10.1016/s0167-9473(03)00140-3]
← All publications