JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

CONCEPTUAL FRAMEWORK FOR AI-DRIVEN STUDENT EVALUATION: INTEGRATING FORMATIVE ASSESSMENT AND LEARNING ANALYTICS

Shen Mingzhu1

1 “Tashkent Institute of Irrigation and Agricultural Mechanization Engineers” National Research University

Zenodo DOI: 10.5281/zenodo.22789179

Keywords

learning analytics student learning evaluation Formative assessment Artificial intelligence human-in-the-loop conceptual framework

Abstract

Formative assessment and learning analytics have evolved into two mature research streams, yet they have not been systematically integrated under AI enablement, and both lack safeguards for validity, fairness, and explainability. To address this gap, this paper proposes the Formative Assessment and Learning Analytics–AI (FALA-AI) conceptual framework, which unifies assessment theory, learning analytics, and AI decision-making through a five-layer plus safeguard-layer architecture. The framework translates theory into computation via a five-strategies × LA-capabilities mapping and embeds human-in-the-loop mechanisms to ensure that AI assists rather than replaces teachers. Instantiation validation on two public datasets—the UCI Student Performance dataset and the Open University Learning Analytics Dataset (OULAD)—demonstrates that the framework’s diagnostic and early-warning pipeline produces actionable signals with AUC values of 0.742–0.969 and a risk-student recall rate of 74.1%. A repeated stratified 50-fold cross-validation (5×10) confirms the statistical robustness of the core proposition that more formative evidence yields more accurate diagnosis (A→B ΔAUC = 0.0073, p ≈ 3.1×10⁻²⁵; B→C ΔAUC = 0.0352, p ≈ 4.0×10⁻⁵⁰). FALA-AI provides a testable unified coordinate system for AI-empowered student evaluation. The framework was instantiated on two public datasets to evaluate diagnostic accuracy, fairness, and reproducibility.

Views: 99 Published: 2026-08-28 Pages: 223-234 Volume: 4 Issue: 4

References

  1. Yu Shengquan. The future role of AI teachers. Open Education Research, 2018, No.24(1), pp.16–28. DOI: 10.13966/j.cnki.kfjyyj.2018.01.003.
  2. McGuire A., Qureshi W., Saad M. A Constructivist Model for Leveraging GenAI Tools for Individualized, Peer-Simulated Feedback on Student Writing. International Journal of Technology in Education, 2024, No.7(2), pp.326–352. DOI: 10.46328/ijte.639.
  3. Stanja J., Gritz W., Krugel J., Hoppe A., Dannemann S. Formative assessment strategies for students' conceptions—The potential of learning analytics. British Journal of Educational Technology, 2023, No.54(1), pp.58–75. DOI: 10.1111/bjet.13288.
  4. Lang C., Siemens G., Wise A.F., Gasevic D., Merceron A. (Eds.). The Handbook of Learning Analytics (2nd ed.). Vancouver: SoLAR, 2022. 280 p.
  5. Swiecki Z., Khosravi H., Chen G., Martinez-Maldonado R., Lodge J.M., Milligan S., Selwyn N., Gasevic D. Assessment in the age of artificial intelligence. Computers and Education: Artificial Intelligence, 2022, No.3, 100075. DOI: 10.1016/j.caeai.2022.100075.
  6. Peng Hongchao, Zhu Zhiting. Human–machine collaborative data wisdom mechanism: Data value alchemy in smart education. Open Education Research, 2018, No.24(2), pp.41–50.
  7. Zheng Qinhua. AI-empowered educational evaluation reform and innovation. Journal of Wuhan University (Natural Science Edition), 2025, No.71(5), pp.589–590. DOI: 10.14188/j.1671-8836.2025.0189.
  8. Chen Li, Lin Wenjing, Zheng Qinhua. Innovative exploration of AI-empowered comprehensive quality assessment for primary and secondary school students. China Examinations, 2025, No.2, pp.41–49. DOI: 10.19360/j.cnki.11-3303/g4.2025.02.005.
  9. Barana A., Conte A., Fissore C., Marchisio M., Rabellino S. Learning analytics to improve formative assessment strategies. Journal of E-Learning and Knowledge Society, 2019, No.15(3), pp.75–88. DOI: 10.20368/1971-8829/1135057.
  10. Dua D., Graff C. UCI Machine Learning Repository [Dataset]. Irvine, CA: University of California, School of Information and Computer Sciences, 2017. DOI: 10.24432/C5SG7M. URL: https://archive.ics.uci.edu/dataset/320/student+performance (accessed: 17.08.2026).
  11. Wu Yao, Li Luyue, Zheng Qinhua. Theoretical reconstruction and practical pathways of AI-empowered student comprehensive quality assessment. China Educational Information Technology, 2025, No.31(10), pp.111–118.
  12. Sajja R., Sermet Y., Cwiertny D., Demir I. Integrating AI and Learning Analytics for Data-Driven Pedagogical Decisions and Personalized Interventions in Education. arXiv, 2023, arXiv:2312.09548 [cs.CY]. URL: https://arxiv.org/abs/2312.09548 (accessed: 17.08.2026).
  13. Earl L. Assessment as Learning: Using Classroom Assessment to Maximize Student Learning. Thousand Oaks: Corwin Press, 2003. 176 p.
  14. Xin Tao, Nie Zhuming, Shi Wenjing, Zhang Sheng. Learning–evaluation integration: Conceptual shift and implementation of educational evaluation. Open Education Research, 2025, No.31(5), pp.30–38. DOI: 10.13966/j.cnki.kfjyyj.2025.05.004.
  15. Chen X., Pi X. Human-in-the-Loop: A Conceptual Framework for Business English Teachers' AI-Empowered Assessment. In: Lecture Notes in Computer Science (Proc. ICWL 2024). Springer, 2025, pp.204–213. DOI: 10.1007/978-981-96-4407-0_17.
  16. Luo Haifeng, Luo Yang, Liu Jian. Educational evaluation reform in the era of artificial intelligence. China Examinations, 2024, No.3, pp.8–17. DOI: 10.19360/j.cnki.11-3303/g4.2024.03.002.
  17. Carless D., Boud D. The development of student feedback literacy: enabling uptake of feedback. Assessment & Evaluation in Higher Education, 2018, No.43(8), pp.1315–1325. DOI: 10.1080/02602938.2018.1463354.
  18. Wang Huaibo, Chai Huanyou, Guo Liming, Liu Zijing, Zheng Qinhua. Intelligent technology-empowered student comprehensive competency assessment: Framework design and implementation path. China Educational Technology, 2022, No.8, pp.16–23.
  19. Khosravi H., Buckingham Shum S., Chen G., Conati C., Tsai Y.-S., Kay J., Knight S., Martinez-Maldonado R., Sadiq S., Gasevic D. Explainable Artificial Intelligence in education. Computers and Education: Artificial Intelligence, 2022, No.3, 100074. DOI: 10.1016/j.caeai.2022.100074.
  20. Shute V.J. Focus on Formative Feedback. Review of Educational Research, 2008, No.78(1), pp.153–189. DOI: 10.3102/0034654307313795.
  21. Kuzilek J., Hlosta M., Zdrahal Z. Open University Learning Analytics dataset. Scientific Data, 2017, No.4, 170171. DOI: 10.1038/sdata.2017.171.
  22. Hadyaoui A., Cheniti-Belcadhi L. IntelliFrame: A Framework for AI-Driven, Adaptive, and Process-Oriented Student Assessments. In: Proc. 20th Int. Conf. on Web Information Systems and Technologies (WEBIST), 2024, pp.441–448. DOI: 10.5220/0013070800003825.
  23. Guo H., Johnson M.S., Ercikan K., Saldivia L., Worthington M. Large-Scale Assessments for Learning: A Human-Centred AI Approach to Contextualizing Test Performance. Journal of Learning Analytics, 2024, No.11(2), pp.229–245. DOI: 10.18608/jla.2024.8007.
  24. Liu Sanya, Hao Xiaohan, Li Qing. A new paradigm of educational research: AI-driven educational science research. Educational Research, 2024, No.45(3), pp.147–159.
  25. Carless D. Exploring learning-oriented assessment processes. Higher Education, 2015, No.69(6), pp.963–976. DOI: 10.1007/s10734-014-9816-z.
  26. Gasevic D., Greiff S., Shaffer D.W. Towards strengthening links between learning analytics and assessment: Challenges and potentials of a promising new bond. Computers in Human Behavior, 2022, No.134, 107304. DOI: 10.1016/j.chb.2022.107304.
  27. Hattie J., Timperley H. The power of feedback. Review of Educational Research, 2007, No.77(1), pp.81–112. DOI: 10.3102/003465430298487.
  28. Gasevic D., Siemens G., Sadiq S. Empowering learners for the age of artificial intelligence (editorial). Computers and Education: Artificial Intelligence, 2023, No.4, 100130. DOI: 10.1016/j.caeai.2023.100130.
  29. Siemens G. Learning analytics: The emergence of a discipline. American Behavioral Scientist, 2013, No.57(10), pp.1380–1400. DOI: 10.1177/0002764213498851.
  30. Black P., Wiliam D. Developing the theory of formative assessment. Educational Assessment, Evaluation and Accountability, 2009, No.21(1), pp.5–31. DOI: 10.1007/s11092-008-9068-5.
  31. Huang Ronghuai, et al. Artificial Intelligence and Future Educational Development. Beijing: Science Press, 2023. 276 p.
  32. Molenaar I. The concept of hybrid human-AI regulation: Exemplifying how to support young learners' self-regulated learning. Computers and Education: Artificial Intelligence, 2022, No.3, 100070. DOI: 10.1016/j.caeai.2022.100070.
  33. Black P., Wiliam D. Inside the Black Box: Raising Standards Through Classroom Assessment. Phi Delta Kappan, 1998, No.80(2), pp.139–148.
  34. Zhang Zhi, Qi Yeguo. Construction of a multi-source multi-dimensional comprehensive quality assessment model based on big data. China Educational Technology, 2017, No.9, pp.69–77.
  35. Tian Aili. Comprehensive quality assessment: Reform and implementation of learning assessment in the intelligent era. China Educational Technology, 2020, No.1, pp.109–113.
  36. Siemens G., Gasevic D., Haythornthwaite C., Dawson S., Shum S.B., Ferguson R., Duval E., Verbert K. Open Learning Analytics: An Integrated & Modularized Platform. Society for Learning Analytics Research (SoLAR), 2011. 119 p.
  37. Buckingham Shum S., Deakin Crick R. Learning dispositions and transferable competencies: pedagogy, modelling and learning analytics. In: Proc. 2nd Int. Conf. on Learning Analytics and Knowledge (LAK '12). New York: ACM, 2012, pp.92–101. DOI: 10.1145/2330601.2330629.
  38. Li Haifeng, Wang Wei. Research on learning analytics: Basic framework and core issues. Open Education Research, 2022, No.28(6), pp.60–71. DOI: 10.13966/j.cnki.kfjyyj.2022.06.007.
  39. Tempelaar D., Rienties B., Giesbers B. Dispositional learning analytics and formative assessment: an inseparable twinship. International Journal of Educational Technology in Higher Education, 2024, No.21(1), 57. DOI: 10.1186/s41239-024-00489-8.