Learning strategies and AI: a new contribution to Educational Quality at high school

The project aimed to strengthen the capacity of participating schools to adopt data-informed and personalised approaches to teaching and learning. More specifically, it sought to digitalise and ad...

The project aimed to strengthen the capacity of participating schools to adopt data-informed and personalised approaches to teaching and learning. More specifically, it sought to digitalise and administer a validated questionnaire on learning strategies in order to obtain a structured and comparable dataset across Italian and Hungarian schools. The project also aimed to develop an initial AI-assisted system capable of analysing students’ responses and generating individualised reports for each learner, offering teachers evidence-based insights into study habits, cognitive preferences and areas requiring support. A further objective was to enhance teachers’ digital and analytical competences, enabling them to interpret the reports and reflect on how learning variability affects classroom dynamics. The project also intended to reinforce cross-country collaboration on innovative educational practices and to provide schools with a model for integrating research-based tools into their internal quality processes. Overall, the project aimed to lay the groundwork for more personalised, inclusive and effective learning environments supported by digital and AI-driven methodologies.

The project was implemented through a coordinated sequence of activities involving all partners. A management structure was established at the outset to organise responsibilities, communication routines and monitoring procedures. The consortium digitalised the validated learning-strategies questionnaire and prepared it for administration in the participating Italian and Hungarian schools. EduBase developed the digital platform used to deliver the questionnaire and display results. After internal testing, schools carried out the data collection phase, supported by instructions and technical assistance. The project team analysed the dataset and produced individual student reports generated through an AI-assisted interpretation of learning styles, study habits and cognitive preferences. Teachers received guidance on how to read and use these reports to better understand learning variability within their classes. Feedback was gathered from schools on the clarity, usefulness and applicability of the outputs. Dissemination activities were carried out through online communication, meetings with stakeholders and the sharing of materials. A final evaluation reviewed the coherence, quality and impact of all activities implemented.