OVERVIEW

Self-regulation improves learning outcomes as revealed by the positive relation between SRL processes and learning measures. Measuring SRL, however, has posed a major challenge to researchers for decades. Various measurement tools and methods have been proposed to help improve the capture of SRL processes, ranging from self-report surveys, think-aloud protocols, and trace-based measurement. Trace-based methods are gaining popularity because they unobtrusively capture cognitive and metacognitive activities in authentic learning environments and have been employed in multiple studies. However, the detection, measurement, and validation of SRL processes with trace data is debatable. Hence, we propose this interactive workshop (aim 1) for interested researchers to examine the current SRL-related work-to-date, explore how they can build upon existing methods of measurement of SRL, and exchange their lessons learnt from different projects. 

While the importance of SRL to learning is widely recognized, effective ways to support learners in regulating their learning remain unclear. Different types of interventions, such as scaffolding, dashboards or personalised feedback, have been designed in learning analytics to effectively support learners’ self-regulated learning and ultimately improve their SRL skills. However, there is limited research into the development of these interventions and how design decisions are associated with the execution of SRL and learning outcomes. Importantly, the complex conditions and contexts when these interventions facilitate and enhance learning are not known. Therefore, this interactive workshop (aim 2) aims to address these challenges by sharing how different interventions can be designed, the potential of the interventions, and/or how effective interventions are in supporting SRL. This will lead to new insights concerning the effectiveness of intervention approaches to facilitate self-regulation. 

The advancement of AI technologies is revolutionising contemporary education. Various AI technologies have been integrated into different educational systems to support student learning, which makes it inevitable that learners will possess co-regulated learning skills with AI. However, the interaction processes between learners and AI remain insufficiently underexplored. This interactive workshop (aim 3) aims to investigate the design of new AI-powered instrumentation tools to detect and measure learning processes during AI interaction, providing insights into the effectiveness of AI in enhancing self-regulation and human-AI co-regulation.

Objectives

From a research perspective, this workshop aims to: i) increase awareness of how tools and data channels can be combined to measure SRL; ii) elicit new approaches for SRL measurement and analysis; iii) understand how student data and AI can generate actionable learning insights; iv) design new forms of SRL scaffolding, dashboards or feedback to facilitate teaching and learning. From the participant's perspective, we expect to: i) improve the knowledge and skills in SRL measurement, learning processes and SRL support; ii) produce a repository of new requirements, considerations and approaches of instruments for SRL; iii) build a research community, foster partnerships, and facilitate collaborative projects; iv) explore opportunities for joint publications (e.g., a journal special issue) and future workshops. In last year’s workshop, we attracted 28 scholars from more than 20 institutions in more than a dozen countries to participate in our workshop. They provided highly positive feedback for the workshop and expressed their willingness to continue the dialogue, such as the research teams from The University of Hong Kong (HKU) and the National Taichung University of Education (NTCU). In their feedback and suggestions, many scholars mentioned the openness of learning platforms and tools, data sharing, and the importance of international collaborative research. Therefore, in this year’s proposal, we emphasise two objectives that are different from other workshops or research tracks in LAK25:

• Provide more hands-on opportunities to experience the measuring and facilitating of SRL using our platform. Participants will explore a learning analytic project and platform (developed and led by organisers, project name hidden for review) integrated with various instrumentation tools and personalised rule-based/GPT-based scaffoldings, and they will be able to explore the data we provided and also the data generated by them, and then co-design possible SRL-related scaffoldings and feedback representations for learners and instructors.

• Initiate and launch an international joint research call based on the same platform and similar tasks. By bringing together like-minded researchers and teachers, we aim to share our platform, tasks, data and project experiences, then discuss an annual international joint study plan. For example, asking different teachers to use the same platform and assign similar tasks in their courses. In this way, the field can collect data that can be compared, triangulated and investigated in multiple contexts, which will greatly facilitate international collaborative research and dialogue, and further deepen our understanding of self-regulated learning.

Supplementary

For more information, please access the FLoRA Engine site: https://www.floraengine.org/home