International Journal of Intelligent Systems and Applications (IJISA)
IJISA Vol. 18, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1152KB)
Artificial Intelligence vs. Traditional Models in Computational Thinking Gap Analytics: A BERT-Driven Approach with XAI Diagnostics
PDF (1152KB), PP.173-190
Views: 0 Downloads: 0
Author(s)
Index Terms
Computational Thinking, Gender Differences, Education, Programming Proficiency, Transformer Models, BERT, Explainable AI, Inferential Statistics, Machine Learning, Deep Learning
Abstract
This study investigates computational thinking (CT) proficiency in programming-based learning environments using a unified analytical framework that combines statistical analysis and predictive modeling. CT proficiency is examined across five pedagogically grounded dimensions—abstraction, decomposition, algorithmic thinking, debugging, and pattern recognition—derived from rubric-based assessment of student work. First, descriptive and inferential statistical analyses are conducted to examine overall CT performance and gender-related patterns, providing correlational insight into group-level differences. Building on this analysis, a transformer-based model (BERT) is employed to predict continuous CT proficiency from students’ code comments and reflective journals, enabling semantic modeling of higher-order reasoning expressed in natural language. The predictive performance of BERT is benchmarked against traditional machine learning and lightweight deep learning baselines. Results show that transformer-based semantic modeling improves predictive accuracy while maintaining interpretability through post hoc explanation methods. Explainable AI techniques are used to identify linguistic and behavioral indicators associated with CT proficiency, and gender-related interpretations are derived through subsequent comparative analysis rather than direct prediction. Overall, the study positions deep learning as a complementary tool to statistical analysis for understanding and predicting CT proficiency.
Cite This Paper
Azeddine Benelrhali, Khalid Berrada, "Artificial Intelligence vs. Traditional Models in Computational Thinking Gap Analytics: A BERT-Driven Approach with XAI Diagnostics", International Journal of Intelligent Systems and Applications (IJISA), Vol.18, No.5, pp.173-190, 2026. DOI:10.5815/ijisa.2026.05.09
Reference
[1]Z. Liu, Z. Gearty, E. Richard, C. H. Orrill, S. Kayumova, and R. Balasubramanian, “Bringing computational thinking into classrooms: a systematic review on supporting teachers in integrating computational thinking into K-12 classrooms,” Int J STEM Educ, vol. 11, no. 1, p. 51, 2024, doi: https://doi.org/10.1186/s40594-024-00510-6
[2]X. Chen and X. Wang, “Computational Thinking Training and Deep Learning Evaluation Model Construction Based on Scratch Modular Programming Course,” Comput Intell Neurosci, vol. 2023, no. 1, p. 3760957, 2023, doi: https://doi.org/10.1155/2023/3760957.
[3]S. Bhatt, K. Verbert, and W. Van Den Noortgate, “A Method for Developing Process-Based Assessments for Computational Thinking Tasks,” Journal of Learning Analytics, vol. 11, no. 2, pp. 157–173, Aug. 2024, doi: 10.18608/jla.2024.8291.
[4]B. Tan, H.-Y. Jin, and M. Cutumisu, “The applications of machine learning in computational thinking assessments: a scoping review,” Computer Science Education, vol. 34, no. 2, pp. 193–221, 2024, doi: 10.1080/08993408.2023.2245687.
[5]B.Azeddine, B.Khalid , "Exploring AI Tools and Large Language Models for Students' Performance Enhancement in Riddle Based Logical Reasoning", International Journal of Modern Education and Computer Science (IJMECS), Vol.17, No.5, pp. 1-28, 2025. doi:10.5815/ijmecs.2025.05.01
[6]B. Palop, I. Díaz, L. J. Rodríguez-Muñiz, and J. J. Santaengracia, “Redefining computational thinking: A holistic framework and its implications for K-12 education,” Educ Inf Technol (Dordr), 2025, doi: 10.1007/s10639-024-13297-4.
[7]R. Tariq, B. M. Aponte Babines, J. Ramirez, I. Alvarez-Icaza, and F. Naseer, “Computational thinking in STEM education: current state-of-the-art and future research directions,” 2024, Frontiers Media SA. doi: 10.3389/fcomp.2024.1480404.
[8]H. Zhang, J. Huang, Z. Li, M. Naik, and E. Xing, “Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming,” May 2023, [Online]. Available: http://arxiv.org/abs/2305.03742
[9]H. Hidayat, A. Komariah, B. B. Wiyono, and Y. Huda, “Impact of the Use of Fuzzy Comprehensive Evaluation Applications towards Computational Thinking Skill Students in Engineering Education,” International Journal of Information and Education Technology, vol. 15, no. 1, pp. 90–100, 2025, doi: 10.18178/ijiet.2025.15.1.2221.
[10]P.-H. Lin and S.-Y. Chen, “Design and Evaluation of a Deep Learning Recommendation Based Augmented Reality System for Teaching Programming and Computational Thinking,” IEEE Access, vol. 8, pp. 45689–45699, 2020, doi: 10.1109/ACCESS.2020.2977679.
[11]D. Li, K. D. Ortegas, and M. White, “Exploring the Computational Effects of Advanced Deep Neural Networks on Logical and Activity Learning for Enhanced Thinking Skills,” Systems 2023, Vol. 11, Page 319, vol. 11, no. 7, p. 319, Jun. 2023, doi: 10.3390/SYSTEMS11070319.
[12]S. Li, S. P. Lajoie, J. Zheng, H. Wu, and H. Cheng, “Automated detection of cognitive engagement to inform the art of staying engaged in problem-solving,” Comput Educ, vol. 163, p. 104114, 2021, doi: https://doi.org/10.1016/j.compedu.2020.104114.
[13]A. Master, D. Tang, D. Forsythe, T. M. Alexander, S. Cheryan, and A. N. Meltzoff, “Gender equity and motivational readiness for computational thinking in early childhood,” Early Child Res Q, vol. 64, pp. 242–254, Jul. 2023, doi: 10.1016/J.ECRESQ.2023.03.004.
[14]L. Hu, “Exploring Gender Differences in Computational Thinking Among K-12 Students: A Meta-Analysis Investigating Influential Factors,” Journal of Educational Computing Research, vol. 62, no. 5, pp. 1358–1384, Sep. 2024, doi: 10.1177/07356331241240670.
[15]R. Richado, S. I. A. Dwiningrum, and A. Wijaya, “Computational Thinking Skill For Mathematics and Attitudes Based on Gender: Comparative and Relationship Analysis,” Pegem Journal of Education and Instruction, vol. 13, no. 2, pp. 345–353, Feb. 2023, doi: 10.47750/PEGEGOG.13.02.38.
[16]S. Jiang and G. K. W. Wong, “Exploring age and gender differences of computational thinkers in primary school: A developmental perspective,” J Comput Assist Learn, vol. 38, no. 1, pp. 60–75, Feb. 2022, doi: 10.1111/JCAL.12591.
[17]S. Lin and G. K. W. Wong, “Gender Differences in Computational Thinking Skills among Primary and Secondary School Students: A Systematic Review,” Education Sciences 2024, Vol. 14, Page 790, vol. 14, no. 7, p. 790, Jul. 2024, doi: 10.3390/EDUCSCI14070790.
[18]G. Ardito, B. Czerkawski, and L. Scollins, “Learning Computational Thinking Together: Effects of Gender Differences in Collaborative Middle School Robotics Program,” TechTrends, vol. 64, no. 3, pp. 373–387, May 2020, doi: 10.1007/S11528-019-00461-8.
[19]Q. Li, Q. Jiang, J. C. Liang, W. Xiong, and W. Zhao, “Engagement predicts computational thinking skills in unplugged activity: Analysis of gender differences,” Think Skills Creat, vol. 52, p. 101537, Jun. 2024, doi: 10.1016/J.TSC.2024.101537.
[20]S. Papavlasopoulou, K. Sharma, and M. N. Giannakos, “Coding activities for children: Coupling eye-tracking with qualitative data to investigate gender differences,” Comput Human Behav, vol. 105, p. 105939, Apr. 2020, doi: 10.1016/J.CHB.2019.03.003.
[21]L. García-Pérez, D. Roldán-Álvarez, and J. M. Cañas, “Does Gender Influence the Learning Process of Computational Thinking in Secondary Education?,” Computer Applications in Engineering Education, vol. 33, no. 3, May 2025, doi: 10.1002/CAE.70050.
[22]L. Sun and J. Liu, “Improving Computational Thinking for Middle School Students Through Python Programming: Interaction Effect Analysis of Grade Level and Gender,” Journal of Educational Computing Research, vol. 63, no. 4, pp. 902–929, Jul. 2025, doi: 10.1177/07356331251332751.
[23]A. M. Gasaymeh and R. AlMohtadi, “College of education students’ perceptions of their computational thinking proficiency,” Front Educ (Lausanne), vol. 9, p. 1478666, Oct. 2024, doi: 10.3389/FEDUC.2024.1478666/BIBTEX.
[24]J. Parraga-Alava and J. Rodas-Silva, “Computational Thinking and Academic Performance Across Different Instructional Modalities in Pre-University Courses: A Data-Driven Study,” Engineering Reports, vol. 7, no. 6, Jun. 2025, doi: 10.1002/ENG2.70203.
[25]A. De la Hoz Serrano, L. V. Melo Niño, A. Álvarez Murillo, M. Á. Martín Tardío, F. Cañada Cañada, and J. Cubero Juánez, “Analysis of Gender Issues in Computational Thinking Approach in Science and Mathematics Learning in Higher Education,” European Journal of Investigation in Health, Psychology and Education 2024, Vol. 14, Pages 2865-2882, vol. 14, no. 11, pp. 2865–2882, Nov. 2024, doi: 10.3390/EJIHPE14110188.
[26]Z. Demir-Kaymak, İ. Duman, C. Randler, and M. B. Horzum, “The Effect of Gender, Grade, Time and Chronotype on Computational Thinking: Longitudinal Study,” Informatics in Education, vol. 21, no. 3, pp. 465–478, 2022, doi: 10.15388/INFEDU.2022.22.
[27]Kwon, S. J. Lee, and K. Kim, “Gender disparities in K-12 computer science education: Status, contributing factors, and instructional approaches,” Computers and Education Open, vol. 8, p. 100253, Jun. 2025, doi: 10.1016/J.CAEO.2025.100253.