A Deep AI Analytics for Targeted Academic Intervention and Engagement Profiling

Authors

  • Thangiah Sathishkumar Deputy Dean, Sricity International University, Sricity, Chitoor Dt.
  • T. Raghavendra Gupta Associate Professor, Hyderabad Institute of Technology And Management
  • S. V. Hemanth Associate Professor, Hyderabad Institute of Technology And Management
  • Dharmendra Kumar Roy Associate Professor, Hyderabad Institute of Technology And Management

DOI:

https://doi.org/10.16920/jeet/2026/v39is2/26019

Keywords:

education, artificial, intelligence, graph, learning, transformers, intervention, multi-model.

Abstract

Indeed, in the rapidly developing field of education, though environments enabling AI-mediated learning are becoming more and more popular, the problem of the feasibility of real-time behavior modeling and forecasting academic achievement analytics remains acute and demands explanatory and adaptive solutions. Conventional learning analytics models tend to fall short of incorporating multi-modal information and do not provide active intervention systems. To overcome such a shortfall, BEACON (Behavioral Engagement-Academic Classifier Optimizer Network) is proposed in this study, which is an original Artificial Intelligence (AI) approach that combines deep sequential learning and explainable graph analytics, utilizing them to model student behavior and predict academic performance on the fly. BEACON has four major sub-processes. They include Multi-modal Data Ingestion Layer, which collects time-series Learning Management System (LMS) logs, facial affective inputs, and engagement data via IoT sensing devices, Behavioral Pattern Graph Construction, where the details are converted to dynamic graphs with Temporal Graph Neural Networks (TGNN), Academic Success Prediction Engine, based on a hybrid Long Short-Term Memory (LSTM)-Transformer sequence model, which predicts course-specific outcomes, and Explainable Intervention Recommender, which uses SHapley Additive exPlanations (SHAP) values to identify student-specific interventions. The evaluation of BEACON was already being carried out using standard real-time dataset and had a perfect 92.4% success finding struggling students in week four of the semester and enhanced positive student results by 18.7%, with student satisfaction on AI-delivered feedback interventions achieving the highest (24.2%) difference. Besides making learning analytics go beyond the traditional dashboard level, this framework supports ethical AI to be accompanied by transparency in a way that makes education sustainable and personalized.

Downloads

Download data is not yet available.

Downloads

Published

2026-02-18

How to Cite

Sathishkumar, T., Raghavendra Gupta, T., Hemanth, S. V., & Roy, D. K. (2026). A Deep AI Analytics for Targeted Academic Intervention and Engagement Profiling. Journal of Engineering Education Transformations, 39(Special Issue 2), 149–158. https://doi.org/10.16920/jeet/2026/v39is2/26019

Issue

Volume 39, Special Issue 2, January 2026

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

References

Aparna, C., Radha, S., Aarthi, C., & Karthick Raghunath, K. M. (2025). HoneyFed Adaptive Deception With Federated Learning Strategy for Next‐Generation Robust MANET Security. Concurrency and Computation: Practice and Experience, 37(9-11), e70100.

Aslan, S., Alyuz, N., Tanriover, C., Mete, S. E., Okur, E., D'Mello, S. K., & Arslan Esme, A. (2019, May). Investigating the impact of a real-time, multimodal student engagement analytics technology in authentic classrooms. In Proceedings of the 2019 chi conference on human factors in computing systems (pp. 1-12).

Bhatia, Dr. A., Bhatia, P., & Sood, D. (2024). Leveraging AI to Transform Online Higher Education: Focusing on Personalized Learning, Assessment, and Student Engagement. International Journal of Management and Humanities, 11(1), 1–6.

Chen, X., Xie, H., Qin, S. J., Wang, F. L., & Hou, Y. (2025). Artificial Intelligence‐Supported Student Engagement Research: Text Mining and Systematic Analysis. European Journal of Education, 60(1), e70008.

Du Plooy, E., Casteleijn, D., & Franzsen, D. (2024). Personalized adaptive learning in higher education: A scoping review of key characteristics and impact on academic performance and engagement. Heliyon, 10(21), e39630.

Guo, H., Johnson, M., Saldivia, L., Worthington, M., & Ercikan, K. (2024). Human-Centered AI for Discovering Student Engagement Profiles on Large-Scale Educational Assessments. Journal of Measurement and Evaluation in Education and Psychology, 15(Special Issue), 282-301.

Hooda, M., Rana, C., Dahiya, O., Rizwan, A., & Hossain, M. S. (2022). Artificial intelligence for assessment and feedback to enhance student success in higher education. Mathematical Problems in Engineering, 2022(1), 5215722.

Li, M., Liu, W., & Chen, C. (2024). Adaptive financial literacy enhancement through cloud-based AI content delivery: Effectiveness and engagement metrics. Annals of Applied Sciences, 5(1), 1-20.

Liu, B., Li, C., & Wan, Z. (2024). Using Explainable AI (XAI) to Identify and Intervene with Students in Need: A Review. In Proceedings of the 2024 3rd International Conference on Artificial Intelligence and Education (pp. 636-641).

Maroju, P. K., & Aragani, V. M. (2025). Predictive analytics in education: Early intervention and proactive support with Gen AI Cloud. In Smart Education and Sustainable Learning Environments in Smart Cities (pp. 317-332). IGI Global Scientific Publishing.

Orji, F. A., Gutierrez, F. J., & Vassileva, J. (2025). Motivation profiles: understanding interplay of persuasive strategies and self-determination theory. Behaviour & Information Technology, 1–20. https://doi.org/10.1080/0144929x.2025.2522200

Papamitsiou, Z., & Economides, A. A. (2014). Learning analytics and educational data mining in practice: A systematic literature review of empirical evidence. Journal of Educational Technology & Society, 17(4), 49-64.

Raghunath, K. M. K., Unhelkar, B., Shankar, S. S., & Chakrabarti, P. (2025). Statistical assessment of an interpretable AI framework for improved disease diagnosis through medical images. Journal of Statistics and Management Systems, 28(1), 193–204.

Saleem, R., & Aslam, M. (2025). A Multi-Faceted Deep Learning Approach for Student Engagement Insights and Adaptive Content Recommendations. IEEE Access, 13, 69236–69256.

Saputra, I., Kurniawan, A., Yanita, M., Yeni Putri, E., & Mahniza, M. (2024). The Evolution of Educational Assessment: How Artificial Intelligence is Shaping the Trends and Future of Learning Evaluation. The Indonesian Journal of Computer Science, 13(6). https://doi.org/10.33022/ijcs.v13i6.4465

Suryadevara, G., & Pachipulusu, P. (2025). Integrating Real-Time Data Streams: Monitoring and Enhancing Education Outcomes. In AI-Enabled Sustainable Innovations in Education and Business (pp. 67-90). IGI Global Scientific Publishing. Whiffe, “GitHub - Whiffe/SCB-dataset: Student Classroom Behavior dataset,” GitHub, 2023. https://github.com/Whiffe/SCB-dataset.git (accessed Jul. 21, 2025).

Kumar, V. Vinoth, KM Karthick Raghunath, Iyappan Perumal, and K. Manikandan. (2025) "Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart-Data Driven Modeling." IEEE Access (2025). IEEE Access 13 (2025): 34435–48.

Li, Rongjie, Songyang Zhang, Dahua Lin, Kai Chen, and Xuming He. (2024) "From pixels to graphs: Open-vocabulary scene graph generation with vision-language models." In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 28076-28086.