- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
A comparative study of traditional, deep, and explainable clustering algorithms for behavioral segmentation of MOOC learners | ||
| Journal of University of Anbar for Pure Science | ||
| Volume 20, Issue 2, August 2026, Pages 320-328 PDF (344.56 K) | ||
| Document Type: Research Paper | ||
| DOI: 10.37652/juaps.2025.164496.1649 | ||
| Author | ||
| Dr.Doreyed Muhammed Al-Kerboly* | ||
| College of Education for Pure Science, University Of Anbar, Anbar, Iraq | ||
| Abstract | ||
| The rapid growth of Massive Open Online Courses (MOOCs) has generated an enormous amount of learner activity data, creating opportunities for personalized learning analytics. However, the complexity, along with the dynamic nature of learners’ behavior, makes the segmentation task challenging. This paper presents a comprehensive traditional evaluation and deep learning-based explainable clustering methods for MOOC learner behavioral segmentation. A large-scale dataset of 50,000 learners, described by behavioral features, was used to benchmark several algorithms, including X-means, agglomerative clustering, DBSCAN, spectral clustering, deep embedded clustering, DEC self-supervised clustering, explainable clustering, k-means with prototype interpretation, and meta-learning clustering. The models were assessed using the silhouette score, the Calinski–Harabasz index, and the Davies–Bouldin index. The results prove that X-Means achieved the best overall performance, with a silhouette of 0.512 and CH of 19,604. However, X-Means achieves a DB of 1.081, outperforming both self-supervised learning approaches and deep learning. Understandable clustering showed strong interpretability for competitive metrics: DB is 1.028, and CH is 23,291, highlighting its potential for actionable insights in educational settings. The DBSCAN performed well, capturing impenetrable structures with a silhouette of 0.458, though at a higher noise fraction. In contrast, spectral clustering exhibited poor separation, with a stability silhouette = –0.325 and DB = 6.096, confirming its limitations for high-dimensional behavioral data. Overall, the results suggest that flexible centroid-based methods, particularly X-means, provide reliable and scalable solutions for segmenting MOOC learners, while enabling more effective personalization through targeted interventions in online education. | ||
| Keywords | ||
| Clustering algorithms; Educational data mining; Learner segmentation; Massive Open online courses (MOOCs); X-means clustering | ||
| References | ||
|
[1] Zhou X, Sun A, Zhang J, Lin D. The Crowd in MOOCs: A Study of Learning Patterns at Scale. Interactive Learning Environments. 2025;33(3):2136-50.10.1080/10494820.2024.2392175 [2] Althibyani HA. Predicting Student Success in MOOCs: A Comprehensive Analysis Using Machine Learning Models. PeerJ Computer Science. 2024;10:e2221.10.7717/peerj-cs.2221 [3] Huang Q, Chen J. Enhancing Academic Performance Prediction with Temporal Graph Networks for Massive Open Online Courses. Journal of Big Data. 2024;11(1):52.10.1186/s40537-024-00918-5 [4] Al-Kerboly DMA, Hamad MM, Dawood OA. Improving Educational Big Data Based on Web Mining and Association Rules. In: AIP Conference Proceedings. vol. 3015. AIP Publishing; 2023. p. 020005.10.1063/5.0188857 [5] Wang R, Ling H, Chen J, Fu H. An Integrated LDA-QFD Approach for Improving Online Course Quality Based on Learners’ Reviews. International Journal of Distance Education Technologies. 2025;23(1):1-24.10.4018/IJDET.371203 [6] Gombert S, Fink A, Giorgashvili T, Jivet I, Di Mitri D, Yau J, et al. From the Automated Assessment of Student Essay Content to Highly Informative Feedback: A Case Study.International Journal of Artificial Intelligence in Education. 2024;34(4):1378-416.10.1007/s40593-023-00387-6 [7] Naseer F, Khan MN, Tahir M, Addas A, Aejaz SMH. Integrating Deep Learning Techniques for Personalized Learning Pathways in Higher Education. Heliyon. 2024;10(11):e32628. 10.1016/j.heliyon.2024.e32628 [8] Wani AA. Comprehensive Analysis of Clustering Algorithms: Exploring Limitations and Innovative Solutions. PeerJ Computer Science. 2024;10:e2286. 10.7717/peerj-cs.2286 [9] AlZuhair MS, Ben Ismail MM, Bchir O. Novel Dual-Constraint-Based Semi-Supervised Deep Clustering Approach. Sensors. 2025;25(8):2622. 10.3390/s25082622 [10] Al-Kerboly DMA, Hamad MM, Dawood OA.Web Mining Algorithms Applied to University Researchers Profiles: A Case Study. International Journal on Technical and Physical Problems of Engineering. 2023;15(4):123-33 [11] Ru Y, Gruninger M, Dou Y. Robust Self Supervised Symmetric Nonnegative Matrix Factorization to the Graph Clustering. Scientific Reports. 2025;15(1):7350.10.1038/s41598-025-92564-x [12] Narang K. MOOC Dataset; 2021.Accessed 2026-08-06. Kaggle dataset. Available from: https : / / www. kaggle . com / datasets / kanikanarang94 / mooc-dataset [13] Goggin SM, Zunder ER. ESCHR: A Hyperparameter-Randomized Ensemble Approach for Robust Clustering across Diverse Datasets. Genome Biology. 2024;25(1):242. Peer-reviewed version of the bioRxiv preprint 10.1101/2023.12.18.571953.10.1186/s13059-024-03386-5 [14] Sánchez Vinces BV, Schubert E, Zimek A, Cordeiro RLF. A Comparative Evaluation of Clustering-Based Outlier Detection.Data Mining and Knowledge Discovery. 2025;39(2):13. 10.1007/s10618-024-01086-z [15] Al-Kerboly DMA, Hamad MM, Dawood OA. Clustering Algorithms Comparison for University of Anbar Researchers’ Google Scholar Profiles. In: 2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT). IEEE; 2023. p. 91-6. 10.1109/AICCIT57614.2023.10217951 [16] Seong M, Park DK. Hamiltonian Formulations of Centroid-Based Clustering. Frontiers in Physics. 2025;13:1544623.10.3389/fphy.2025.1544623 [17] Liu Y, Lin X, Chen Y, Cheng R. Multi-Order Graph Clustering with Adaptive Node-Level Weight Learning. Pattern Recognition. 2024;156:110843. 10.1016/j.patcog.2024.110843 [18] Al-Kerboly DMA, Hamad MM, Dawood OA.Big Data Applications Based on Web Mining Techniques and Recommender Systems: Survey.In: AIP Conference Proceedings. vol. 3009. AIP Publishing; 2024. p. 020010.10.1063/5.0190403 [19] Premkumar M, Sinha G, Ramasamy MD, Sahu S, Subramanyam CB, Sowmya R, et al. Augmented Weighted K-Means Grey Wolf Optimizer: An Enhanced Metaheuristic Algorithm for Data Clustering Problems.Scientific Reports. 2024;14(1):5434. 10.1038/s41598-024-55619-z [20] Li J, Chen F.Gauging Road Safety Advances Using a Hybrid EWM–PROMETHEE II–DBSCAN Model with Machine Learning.Frontiers in Public Health. 2024;12:1413031.10.3389/fpubh.2024.1413031 [21] Fang C, Zhou L, Gu X, Liu X, Werner M.A Data Driven Approach to Urban Area Delineation Using Multi Source Geospatial Data. Scientific Reports. 2025;15(1):8708.10.1038/s41598-025-93366-x [22] Yang Y, Wang X, Wu X, Lan X, Su T, Guo Y. A Target Detection Algorithm Based on Fusing Radar with a Camera in the Presence of a Fluctuating Signal Intensity. Remote Sensing. 2024;16(18):3356. 10.3390/rs16183356 [23] Ghorvei M, Karhu T, Hietakoste S, Ferreira-Santos D, Hrubos-Strøm H, Islind AS, et al.A Comparative Analysis of Unsupervised Machine-Learning Methods in PSG-Related Phenotyping. Journal of Sleep Research. 2025;34(3):e14349.10.1111/jsr.14349 [24] Prokop P, Dráždilová P, Platoš J. Overlapping Community Detection in Weighted Networks via Hierarchical Clustering. PLOS ONE. 2024;19(10):e0312596. 10.1371/journal.pone.0312596 [25] Sieranoja S, Fränti P. Fast Agglomerative Clustering Using Approximate Traveling Salesman Solutions. Journal of Big Data. 2025;12(1):21. 10.1186/s40537-024-01053-x [26] Khosravi Y, Hosseinali F, Adresi M. Identifying Accident Prone Areas and Factors Influencing the Severity of Crashes Using Machine Learning and Spatial Analyses.Scientific Reports. 2024;14(1):29836.10.1038/s41598-024-81121-7 [27] de Kok JWTM, van Rosmalen F, Koeze J, Keus F, van Kuijk SMJ, Castela Forte J, et al. Deep Embedded Clustering Generalisability and Adaptation for Integrating Mixed Datatypes: Two Critical Care Cohorts. Scientific Reports. 2024;14(1):1045. 10.1038/s41598-024-51699-z [28] Duong PB, Van Herbruggen B, Bröring A, Shahid A, De Poorter E.Error Mitigation for TDoA UWB Indoor Localization Using Unsupervised Machine Learning. IEEE Sensors Journal. 2025;25(1):1959-68.10.1109/JSEN.2024.3496086 [29] Priya RS, Vani K.Vegetation Change Detection and Recovery Assessment Based on Post-Fire Satellite Imagery Using Deep Learning.Scientific Reports. 2024;14(1):12611.10.1038/s41598-024-63047-2 [30] Akgüller Ö, Balcı MA, Cioca G. Clustering Molecules at a Large Scale: Integrating Spectral Geometry with Deep Learning. Molecules. 2024;29(16):3902.10.3390/molecules29163902 [31] Yadalam PK, Natarajan PM, Ardila CM. Variational Graph Autoencoder for Reconstructed Transcriptomic Data Associated with NLRP3-Mediated Pyroptosis in Periodontitis. Scientific Reports. 2025;15(1):1962.10.1038/s41598-025-86455-4 [32] Nagar S, Farahbakhsh E, Awange J, Chandra R. Remote Sensing Framework for Geological Mapping via Stacked Autoencoders and Clustering. Advances in Space Research. 2024;74(10):4502-16. 10.1016/j.asr.2024.09.013 [33] Petukhova A, Matos-Carvalho JP, Fachada N. Text Clustering with Large Language Model Embeddings. International Journal of Cognitive Computing in Engineering. 2025;6:100-8. 10.1016/j.ijcce.2024.11.004 [34] Bombina, P., Tally, D., Abrams, Z. B., & Coombes, K. R. (2024). SillyPutty: Improved clustering by optimizing the silhouette width. PloS one, 19(6), e0300358 [35] Amin MM, Sani NS, Nasrudin MF, Abdullah S, Chhabra A, Abd Kadir F. Clustering Analysis for Classifying Fake Real Estate Listings.PeerJ Computer Science. 2024;10:e2019.10.7717/peerj-cs.2019 [36] Al-Kerboly DMA, Al-Kerboly DZF.A Comparative Study of Clustering Algorithms for Profiling Researchers in Universities Through Google Scholar. In: 2024 IEEE 3rd International Conference on Computing and Machine Intelligence (ICMI). IEEE; 2024. p. 1-5.10.1109/ICMI60790.2024.10585953 [37] Yang D, Wang J, He J, Zhao C. A Clustering Mining Method for Sports Behavior Characteristics of Athletes Based on the Ant Colony Optimization.Heliyon. 2024;10(12):e33297. 10.1016/j.heliyon.2024.e33297 | ||
|
Statistics Article View: 139 PDF Download: 115 |
||