Techniques for using artificial intelligence to foster active learning

AI-powered learning analytics refers to the systematic collection and analysis of data on student learning using artificial intelligence algorithms. These algorithms enable a deeper understanding of the learning process, identify behavioural patterns, and predict potential risks in achieving educational goals.

The results of such analysis are used to provide personalised recommendations to students and timely pedagogical interventions by teachers. As a result, students gain clearer insight into their own learning patterns, make more informed decisions about next steps, and reflect on their progress.

This approach directly encourages active learning and the development of academic autonomy, as the student becomes an active decision-maker in their own learning.

AI-powered learning analytics supports self-management of learning, but does not manage learning for the student.

Example of an AI tool:

IntelliBoard is a learning analytics system that can be integrated with Moodle and other higher education learning management systems. It uses elements of artificial intelligence, particularly machine learning methods, to analyse student engagement and performance and identify patterns that indicate the need for additional support. It provides students and instructors with visual progress reports and recommendations for improving the learning process. More advanced analytical functionalities are available in the commercial version, and an institutional license is required for full use.

Example in a higher education environment:

In the course “Introduction to Programming”, students regularly solve short problem tasks in a digital learning management system (LMS) that uses artificial intelligence to analyse data about their activities. The system monitors the frequency of access to materials, the level of success in quizzes, and the timeliness of assignment submissions, and shows students visual indicators of progress in relation to learning outcomes.

If the system notices that an individual student is lagging in a certain type of task or shows a decline in engagement, it provides a personalised recommendation, such as:

• Review of additional materials
• Targeted exercises
• Reminder of a deadline or activity in which they did not participate

Based on these insights, the student plans further activities, adjusts their learning strategy, and reflects on progress over time. The teacher uses aggregated data to initiate discussions about effective learning methods and to provide timely support to students who need additional help.

This approach encourages active learning because students rely on information about their own progress, make informed decisions, and take responsibility for the quality of their learning.

The use of AI-powered learning analytics contributes to active learning because students actively monitor their progress, adjust learning strategies, and develop responsibility for achieving learning outcomes. At the same time, the teacher uses analytical insights to direct support to students, ensuring timely and effective adjustments in the teaching process.