Enhancing the Human Touch: A Data-Driven Analysis of Student Archetypes in an AI-Augmented Classroom

Authors

  • Gomathi Thiyagarajan Dept. of Computer Application, CMR Institute of Technology, Bengaluru
  • Avishek Nandi Dept. of Computer Application, Manipal University Jaipur, Jaipur
  • Avichandra Singh Ningthoujam Dept. of Computer Application, Manipal University Jaipur, Jaipur

DOI:

https://doi.org/10.16920/jeet/2026/v39is2/26030

Keywords:

AI in education; educational data mining; K-Means clustering; learning analytics; student archetypes; student-centric learning.

Abstract

In the contemporary landscape of Indian higher education, the incorporation of Artificial Intelligence (AI) of- fers both unparalleled possibilities and considerable educational challenges. A principal concern is the potential diminution of the essential ‘human touch’ which is foundational to effective teach- ing. This study addresses this issue by proposing a data-driven framework to identify distinct student archetypes within an AI- augmented learning environment. We leverage a comprehensive dataset comprising 638 undergraduate engineering students, which includes prior academic records, weekly performance metrics, and system interaction logs, upon which the K-Means clustering algorithm is applied. Our analysis successfully delin- eates four distinct student archetypes: the ‘High-Achieving and Consistent’, the ‘Diligent but Struggling’, the ‘Disengaged and At-Risk’, and the ‘Erratic Performer’. By characterizing these cohorts based on their academic, behavioral, and engagement patterns, we provide educators with actionable insights. These insights empower instructors to transcend monolithic teaching strategies and implement targeted, personalised interventions. Such a strategy ensures that while AI manages scalability, the educator’s role is amplified, enabling them to provide a more nuanced, empathetic, and effective human touch where it is most critically needed. This work proposes a symbiotic model wherein AI-driven analytics and human pedagogy converge to foster a more supportive and effective learning ecosystem.

Downloads

Download data is not yet available.

Downloads

Published

2026-02-18

How to Cite

Thiyagarajan, G., Nandi, A., & Ningthoujam, A. S. (2026). Enhancing the Human Touch: A Data-Driven Analysis of Student Archetypes in an AI-Augmented Classroom. Journal of Engineering Education Transformations, 39(Special Issue 2), 244–251. https://doi.org/10.16920/jeet/2026/v39is2/26030

Issue

Volume 39, Special Issue 2, January 2026

Section

Articles
Crossref
Scopus
Google Scholar
Europe PMC

References

Cristina Alonso-Ferna´ndez, Ana Rus Cano, Antonio Calvo- Morata, Manuel Freire, Iva´n Mart´ınez-Ortiz, and Baltasar Ferna´ndez-Manjo´n. Lessons learned applying learning an- alytics to assess serious games. Computers in Human Behavior, 96:65–74, 2019.

Svenja Bedenlier, Melissa Bond, Katja Buntins, Olaf Zawacki- Richter, and Michael Kerres. Learning by Doing? Reflec- tions on Conducting a Systematic Review in the Field of Educational Technology, pages 111–127. Springer Fachme- dien Wiesbaden, Wiesbaden, 2020.

Ming Chen and Zhi Liu. Predicting performance of students by optimizing tree components of random forest using genetic algorithm. Heliyon, 10(12):e32570, 2024.

Clayton Cohn, Eduardo Davalos, Caleb Vatral, Joyce Horn Fonteles, Hanchen David Wang, Meiyi Ma, and Gau- tam Biswas. Multimodal methods for analyzing learning and training environments: A systematic literature review. CoRR, abs/2408.14491, 2024.

Joseph K. E. Edumadze and Desmond W. Govender. The community of inquiry as a tool for measuring student en- gagement in blended massive open online courses (moocs): a case study of university students in a developing country. Smart Learning Environments, 11(1):19, 2024.

Joa˜o Gabriel Correˆa Kru¨ger, Alceu de Souza Britto, and Jean Paul Barddal. An explainable machine learning ap- proach for student dropout prediction. Expert Systems with Applications, 233:120933, 2023.

Harikumar Pallathadka, Shikha Jain, Suraj Kamble, and Ko- rakod Tongkachok. Educational data mining: A comprehen- sive review and future challenges. ECS Transactions, 107: 16129–16136, April 2022.

Rory Quinn and Geraldine Gray. Prediction of student academic performance using moodle data from a further education setting. Irish Journal of Technology Enhanced Learning, 5, October 2019.

Sabine Seufert, Christoph Meier, Matthias Soellner, and Ro- man Rietsche. A pedagogical perspective on big data and learning analytics: A conceptual model for digital learning support. Technology, Knowledge and Learning, 24:599–619, 2019.

Omid Speily, Alireza Rezvanian, Ardalan Ghasemzadeh, Ali M. Saghiri, and S. Mehdi Vahidipour. Lurkers Versus Posters: Investigation of the Participation Behaviors in Online Learning Communities, pages 269–298. January 2020.

Teo Susnjak, G. S. Ramaswami, and Anuradha Mathrani. Learning analytics dashboard: a tool for providing action- able insights to learners. International Journal of Educa- tional Technology in Higher Education, 19(1):12, 2022.

Shan Wang, Fang Wang, Zhen Zhu, Jingxuan Wang, Tam Tran, and Zhao Du. Artificial intelligence in education: A sys- tematic literature review. Expert Systems with Applications, 252:124167, 2024.

Jun Xiao, Ming Chen, Yue Yang, et al. An exploratory multimodal study of the roles of teacher-student interaction and emotion in academic performance in online classrooms. Education and Information Technologies, 30:15507–15527, 2025.

Saijing Zheng, Mary Beth Rosson, Patrick C. Shih, and John M. Carroll. Understanding student motivation, behav- iors and perceptions in moocs. In Proceedings of the 18th ACM Conference on Computer Supported Cooperative Work Social Computing (CSCW ’15), pages 1882–1895. ACM, 2015.