Speaker
Description
Introduction
One of the challenges faced by teachers has always been to identify which tasks provide the most effective and efficient pathways for students. By using ML and predictive analytical tools, it is possible to create a computer program that can see through this and learn to recognise which tasks to assign to students. The following research topic aims to develop a computer programme which provides personalized learning path for secondary school students based on their prior knowledge and competencies.
The integration of ICT in education has transformed learning processes, enhancing student engagement and motivation. Interactive platforms and online learning systems can foster active participation and independent learning. ICT-based approaches support differentiated and personalised teaching, contributing to improved learning outcomes. The aim of improving educational effectiveness suggests that the use of ICT can facilitate innovative pedagogical practices, which can lead to more dynamic and student-centred learning environments. [1]
ML methods can be used to evaluate and improve the effectiveness of teaching and learning processes. By integrating ML with traditional assessment methods, teachers can optimise learning activities and assess the impact of their teaching strategies. This data-driven framework supports better student outcomes and enables more informed teaching decisions, improving educational practice. [2]
Schematic of the algorithm
First of all an assessment of students' general competencies in mathematics, literacy, and science is conducted, as these skills can influence the optimal pathways for academic progression. After that, students fill a subject-specific test – mechanics, in our study. Based on the results of the test, the algorithm identifies common misconceptions and errors and then generates a personalized set of practice tasks aimed at correcting them. The system monitors students’ performance on these tasks and provides targeted feedback for them. Following this, students retake the same test as before. Throughout this process, the algorithm tracks the input parameters (competency levels), test performance, solution of the practice tasks, and progress metrics. Based on the extensive data generated through repeated fills, artificial intelligence can identify patterns and correlations, refining the practice process, and facilitating personalized learning. This cycle can – and should – be repeated to further enhance learning outcomes.
[1] Timotheou, S. et al.(2023). Impacts of digital technologies on education and factors influencing schools’ digital capacity and transformation: A literature review. Education and Information Technologies, 28(6), 6695–6726. https://doi.org/10.1007/s10639-022-11431-8
[2] Sabharwal, R. et al.(2024). Evaluating teachers’ effectiveness in classrooms: an ML-based assessment portfolio. Social Network Analysis and Mining, 14(1), 28. https://doi.org/10.1007/s13278-023-01195-5
| Contribution categories - primary focus | Primary and secondary school |
|---|---|
| Contribution categories - type | Application (shared experience, activity suggestions) |