Adaptive Mobile Crossword Application with Intelligent User Profiling Using Supervised Machine Learning


Authors : Naji Shukri Alzaza

Volume/Issue : Volume 11 - 2026, Issue 2 - February

Google Scholar : https://tinyurl.com/76k5hzmu

Scribd : https://tinyurl.com/nhjj7e5n

DOI : https://doi.org/10.38124/ijisrt/26feb546

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This study introduces Romooz, an Arabic-language mobile crossword application designed to address the limited adaptive personalization in existing Arabic educational games. The system integrates supervised machine learning (ML) to perform intelligent user profiling and support adaptive mobile learning (m-learning). Real-time gameplay data—such as completion time, error count, hint usage, and scoring—are captured and used to classify learners into five pedagogically meaningful profiles: Novice, Basic Learner, Independent, Strategic Learner, and Expert. A dataset of 1,707 structured interaction records from 100 users over 800+ sessions was analyzed. Six supervised ML algorithms—K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree, Support Vector Machine (SVM), Random Forest, and Multi-Layer Perceptron (MLP)— were trained using stratified 10-fold cross-validation. Random Forest and MLP achieved the highest accuracies (92.3% and 91.7%), confirming the robustness of ensemble and neural approaches in modeling learner behavior. Findings validate the feasibility of ML-powered adaptive content delivery, dynamic feedback, and culturally relevant Arabic m-learning environments.

Keywords : Adaptive Learning, Supervised Machine Learning in Education, User Profiling, Crossword, Arabic m-Learning.

References :

  1. Y. Jing, L. Zhao, K. Zhu, H. Wang, C. Wang and Q. Xia, "Research Landscape of Adaptive Learning in Education: A Bibliometric Study on Research Publications from 2000 to 2022," Sustainability, vol. 15, no. 4, 2023.
  2. D. Debeer, S. Vanbecelaere, W. V. D. Noortgate, B. Reynvoet und F. Depaepe, „The effect of adaptivity in digital learning technologies. Modelling learning efficiency using data from an educational game,“ British Journal of Educational Technology (BJET), Bd. 52, Nr. 5, pp. 1881-1897, 2021.
  3. J. Ren und Shaomin Wu, „Prediction of user temporal interactions with online course platforms using deep learning algorithms,“ Computers and Education: Artificial Intelligence, Bd. 4, pp. 100-133, 2023.
  4. R. S. Baker und P. S. Inventado, „Educational Data Mining and Learning Analytics,“ in Learning Analytics, Springer New York, 2014, p. 61–75.
  5. Gligorea, M. Cioca, R. Oancea, A.-T. Gorski, H. Gorski und P. Tudorache, „Adaptive Learning Using Artificial Intelligence in e-Learning: A Literature Review,“ Education Sciences, Bd. 13, Nr. 12, p. 1216, 2023.
  6. M.-H. Hsu, T.-M. Chan und C.-S. Yu, „Termbot: A Chatbot-Based Crossword Game for Gamified Medical Terminology Learning,“ Bd. 20, Nr. 5, p. 4185, 2023.
  7. Bechtold, SEEKH: Automated Crossword Puzzle Generation for Educational Purposes (Master's thesis), University of California, Berkeley, 2020.
  8. J. Sandberg, T. De Jong und H. Van Rijn, „The Smart Vocabulary Trainer: A mobile app with adaptive learning features,“ in 9th European Conference on Technology Enhanced Learning, 2014.
  9. K. Zeinalipour, M. Z. Saad, M. Maggini und M. Gori, „From Arabic Text to Puzzles: LLM-Driven Development of Arabic Educational Crosswords,“ arXiv preprint arXiv:2501.11035, 2025.
  10. Y. Farhaoui, T. Herawan, A. L. Imoize und A. E. Allaoui, „45. Farhaoui, Y., Herawan, T., Imoize, A. L., & El Allaoui, A. (2025). Intersection of Artificial Intelligence, Data Science, and Cutting-Edge Technologies: From Concepts to Applications in Smart Environment (ICAISE 2024),“ 2025.
  11. Z. A. Pardos und N. T. Heffernan, „KT-IDEM: Introducing Item Difficulty to the Knowledge Tracing Model,“ in User Modeling, Adaption and Personalization, Berlin, Heidelberg, Springer, 2011, p. 243–254.
  12. M. Verghis, B. Jose, S. P. R, S. M. Varghese, M. S und S. K. S, „Beyond Personalization: Autonomy and Agency in Intelligent Systems Education,“ Frontiers in Education, 2025.
  13. K. Toomla und D. Hooshyar, „Generalizable Framework for Tracing and Supporting Self-Regulated Learning in K-12 Digital Learning,“ in 3rd International Symposium on Digital Transformation, Växjö, 2024.
  14. H. Lahza, H. Khosravi und G. Demartini, „Analytics of learning tactics and strategies in an online learnersourcing environment,“ Journal of Computer Assisted Learning (JCAL), Bd. 39, Nr. 1, pp. 94-112, 2023.
  15. N. S. Alzaza und A. R. Yaakub, „Students’ awareness and requirements of mobile learning services in the higher education environment. American Journal of Economics and Business Administration, 3(1), 95–100.,“ merican Journal of Economics and Business Administration (AJEBA), Bd. 3, Nr. 1, pp. 95-100, 2011.
  16. Bosakova-Ardenska und D. Andreev, „Design and Implementation of Educational Game Using Crossword Principles,“ Engineering Proceedings, Bd. 70, Nr. 1, 2024.
  17. R. Mustapha, G. Soukaina und Q. & Mohammed, „Towards an Adaptive e-Learning System Based on Deep Learner Profile, Machine Learning Approach, and Reinforcement Learning,“ International Journal of Advanced Computer Science and Applications, Bd. 14, Nr. 5, 2023.
  18. K. Abhirami und M. Devi, „Student Behavior Modeling for an E-Learning System Offering Personalized Learning Experiences,“ Computer Systems Science & Engineering, 2022.
  19. K. R. Premlatha, B. Dharani und T. V. Geetha, „Dynamic learner profiling and automatic learner classification for adaptive e-learning environment,“ Interactive Learning Environments, Bd. 24, Nr. 6, pp. 1054-1075, 2014.
  20. Q. Huang und J. Chen, „Enhancing academic performance prediction with temporal graph networks for massive open online courses,“ Journal of Big Data, Springer Nature Link, Bd. 11, 2024.
  21. N. F. Ab Rahman, S. L. Wang und N. Khalid, „Ensemble Learning In Educational Data Analysis For Improved Prediction Of Student Performance: A Literature Review,“ International Journal of Modern Education, Bd. 7, Nr. 24, pp. 887-902, 2025.
  22. N. S. Alzaza, „Assessment of the Contingency Theory on Performance Mobile Learn-ing in the Palestinian Higher Education Institutions during Coronavirus Pandemic: Moodle Case Study,“ International Journal of Novel Research in Engineering and Science, Bd. 9, Nr. 1, pp. 14-23, 2022.
  23. J. Fan und C. Li, „Factors Influencing the Behavioral Intention to Use Mobile Learning Platform in Higher Education of Changsha, China,“ nternational Journal of Sociologies and Anthropologies Science Reviews, Bd. 5, Nr. 1, pp. 821-836, 2025.
  24. C. Romero und S. Ventura, „Educational data mining and learning analytics: An updated survey,“ arXiv:2402.07956 , 2024.
  25. T. T. T. Phuong, N. D. Nguyen, D. N. Van, H. N. T. Thu und T. N. Chi, „Factors influencing the use of digital games in teaching: An exploratory study in the context of digital transformation in northern Vietnam,“ International Journal of Emerging Technologies in Learning, Bd. 18, Nr. 8, pp. 164-182, 2023.
  26. J. Martin, Rapid Application Development, Macmillan Coll Div, 1991.
  27. L. Sun, C. Li, B. Liu und Y. Zhang, „Class-Driven Graph Attention Network for Multi-Label Time Series Classification in Mobile Health Digital Twins,“ IEEE Journal on Selected Areas in Communications, Bd. 41, Nr. 10, pp. 3267-3278, 2023.
  28. Y. Bengio und Y. Grandvalet, „No unbiased estimator of the variance of k-fold cross-validation. Machine Learning,“ Journal of Machine Learning Research, Bd. 4, p. 1089–1105, 2004.
  29. S. Abdi, H. Khosravi, S. Sadiq und D. Gasevic, „A Multivariate Elo-based Learner Model for Adaptive Educational Systems,“ Computers and Society, 2019.
  30. V. Aleven, E. A. McLaughlin, R. A. Glenn und K. R. Koedinger, „Instruction based on adaptive learning technologies,“ in Handbook of Research on Learning and Instruction, Bd. 2nd, New York, Routledge, 2016, p. 522–560.
  31. Roll, R. S. Baker, V. Aleven und K. R. Koedinger, „On the Benefits of Seeking (and Avoiding) Help in Online Problem-Solving Environments,“ Journal of the Learning Sciences, Bd. 23, Nr. 4, pp. 537-560, 2014.
  32. H. Khosravi, S. B. Shum, G. Chen, C. Conati, Y.-S. Tsai, J. Kay, S. Knight, R. Martinez-Maldonado, S. Sadiq und D. Gašević, „Explainable Artificial Intelligence in education,“ Computers and Education: Artificial Intelligence, Bd. 3, 2022.
  33. Hernández-Blanco, B. Herrera-Flores, D. Tomás und B. Navarro-Colorado, „A Systematic Review of Deep Learning Approaches to Educational Data Mining,“ Complexity, p. 1–22, 2019.
  34. Roll, V. Aleven, B. M. McLaren und K. R. Koedinger, „Improving students’ help-seeking skills using metacognitive feedback in an intelligent tutoring system,“ Learning and Instruction, Bd. 21, Nr. 2, pp. 267-280, 2011.
  35. J. Han, J. Pei und H. Tong, Data Mining: Concepts and Techniques, 4th Hrsg., Morgan Kaufmann, 2022.
  36. C. M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics), Springer, 2006.
  37. R. Kohavi, „A study of cross-validation and bootstrap for accuracy estimation and model selection,“ in 14th International Joint Conference on Artificial Intelligence, 1995.

This study introduces Romooz, an Arabic-language mobile crossword application designed to address the limited adaptive personalization in existing Arabic educational games. The system integrates supervised machine learning (ML) to perform intelligent user profiling and support adaptive mobile learning (m-learning). Real-time gameplay data—such as completion time, error count, hint usage, and scoring—are captured and used to classify learners into five pedagogically meaningful profiles: Novice, Basic Learner, Independent, Strategic Learner, and Expert. A dataset of 1,707 structured interaction records from 100 users over 800+ sessions was analyzed. Six supervised ML algorithms—K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree, Support Vector Machine (SVM), Random Forest, and Multi-Layer Perceptron (MLP)— were trained using stratified 10-fold cross-validation. Random Forest and MLP achieved the highest accuracies (92.3% and 91.7%), confirming the robustness of ensemble and neural approaches in modeling learner behavior. Findings validate the feasibility of ML-powered adaptive content delivery, dynamic feedback, and culturally relevant Arabic m-learning environments.

Keywords : Adaptive Learning, Supervised Machine Learning in Education, User Profiling, Crossword, Arabic m-Learning.

Paper Submission Last Date
28 - February - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe