Artificial Intelligence (A.I.) has increasingly become an essential tool in modern education, offering innovative ways to enhance teaching, learning, and student well-being. Through Computational Intelligence (C.I.), researchers can address complex problems.
In this fashion, the paper of Zervoudakis et al. (2019) introduces an approach for organizing students into effective teams by employing Particle Swarm Optimization. This method draws on swarm intelligence to iteratively determine optimal groupings, taking into account academic profiles, learning goals, and other relevant factors for differentiated instruction purposes. The resulting clusters balance group size and composition, helping educators foster constructive peer collaboration while reducing the time and subjectivity involved in manual grouping processes.
The paper of Mastrothanasis et al. (2023) applies a Mayfly-based algorithm to categorize students according to their emotional states during theatrical performances. Through a clustering process, students experiencing heightened levels of performance anxiety are quickly identified. By comparing Mayfly-driven results with those from other optimization techniques, the study demonstrates that this approach detects patterns effectively, enabling educators to design interventions that help children overcome anxiety-related challenges and fully engage in creative artistic experiences.
The paper of Mastrothanasis et al. (2024) focuses on virtual theater contexts, where a newly conceived Flying Fox Optimizer systematically places students into compatible teams. Participants’ individual attributes, such as technological fluency, creative preferences, and social tendencies, are processed and analyzed without the need for extensive manual oversight. In digital drama or metaverse environments, this process ensures that performance teams are balanced, cohesive, and capable of thriving in immersive, collaborative digital spaces.
The paper of Kyriakidis et al. (2024) focuses on the experiences of university instructors navigating remote teaching during Covid-19 pandemic. The study combines large-scale surveys with advanced natural language processing, specifically topic modeling, to uncover key difficulties and strategies embraced by educators. Although problems such as inadequate infrastructure or limited interaction arose, instructors reported discovering valuable digital resources and pedagogical methods that could outlast the pandemic era, offering insights into how institutions might enhance their remote offerings and future emergency readiness.
The paper of Shaikh et al. (2024) proposes an enhanced Mayfly Optimization Algorithm to cluster and analyze student anxiety in more refined detail. The approach tailors both exploration and exploitation processes to handle multi-dimensional data, improving upon limitations found in earlier clustering methods. By sorting students into groups based on their characteristics professionals can quickly detect those who require specialized guidance, ensuring timely support that promotes both mental well-being and academic success.
References
Kyriakidis, A., Zervoudakis, K., Krassadaki, E., & Tsafarakis, S. (2024). Exploring the Impact of ICT on Higher Education Teaching During COVID-19: Identifying Barriers and Opportunities Through Advanced Text Analysis on Instructors’ Experiences. Journal of the Knowledge Economy, 1–31. https://doi.org/10.1007/S13132-024-02346-5
Mastrothanasis, K., Zervoudakis, K., & Kladaki, M. (2024). An application of Computational Intelligence in group formation for digital drama education. Iran Journal of Computer Science, 7(3), 551–563. https://doi.org/10.1007/S42044-024-00186-9
Mastrothanasis, K., Zervoudakis, K., Kladaki, M., & Tsafarakis, S. (2023). A bio-inspired computational classifier system for the evaluation of children’s theatrical anxiety at school. Education and Information Technologies, 1–24. https://doi.org/10.1007/s10639-023-11645-4
Shaikh, M. S., Zheng, G., Wang, C., Wang, C., Dong, X., & Zervoudakis, K. (2024). A classification system based on improved global exploration and convergence to examine student psychological fitness. Scientific Reports, 14(1), 1–22. https://doi.org/10.1038/s41598-024-78781-w
Zervoudakis, K., Mastrothanasis, K., & Tsafarakis, S. (2019). Forming automatic groups of learners using particle swarm optimization for applications of differentiated instruction. Computer Applications in Engineering Education, 28(2), 282–292. https://doi.org/10.1002/cae.22191