Research is a central part of SAILeR and provides the foundation for the development of new approaches and tools for learning design, AI-supported education and learning analytics. The project combines literature reviews, empirical research with educators, conceptual development, user evaluation and scientific dissemination, with research findings feeding directly into the further development of the Balanced Design Planning (BDP) tool.
Several research directions have already resulted in scientific publications and conference presentations.
Prioritising Learning Outcomes
One research strand investigates how the relative importance of learning outcomes can be determined and incorporated into learning design. The paper “Review of Learning Outcomes Prioritisation Approaches”, presented at CECIIS 2026, examines different approaches to learning outcome prioritisation.
This research is directly connected with the development of new BDP functionalities for assigning learning outcome weights. BDP now supports three approaches: equal weighting, manual weighting and the SWING method.
Divjak, Blaženka; Kadoić, Nikola; Svetec, Barbi; Vlahek, Dino: Review of Learning Outcomes Prioritisation Approaches. 37th CECIIS – Central European Conference on Information and Intelligent Systems, Varaždin, Croatia.
AI-Supported Study Programme Design
SAILeR research also explores how learning design can be extended beyond individual courses to the study programme level and how AI can support curriculum development.
The paper “Study Program Curriculum Development with AI”, presented at AIED 2026, is connected with the ongoing development of study programme design functionalities in BDP. These functionalities are already being applied in an initial case study involving the redesign of a postgraduate-level study programme, while further development and case studies are planned.
Divjak, Blaženka; Vondra, Petra; Grabar, Darko; Svetec, Barbi; Bađari, Josipa: Study Program Curriculum Development with AI // 27th International Conference AIED 2026 Proceedings, Part III / Blanchard, Emmanuel G.; Chen, Guanliang; Chi, Min et al. (ur.). Cham: Springer, 2026. str. 188-197
AI and Learning Analytics Infrastructure
A third research direction addresses the connection between artificial intelligence and learning analytics in higher education. The paper “AI-Driven Conceptual Infrastructure Model of Learning Analytics in Higher Education” was presented at CSEDU 2026 and contributes to the project's broader research on AI-supported learning design and learning analytics. The periodic report identifies this publication as one of the scientific outputs accompanying the ongoing development of the AI assistant and related BDP functionalities.
Vondra, Petra; Bađari, Josipa; Grabar, Darko; Svetec, Barbi; Divjak, Blaženka: AI-Driven Conceptual Infrastructure Model of Learning Analytics in Higher Education // 18th International Conference on Computer Supported Education (CSEDU 2026) Benidorm, Spain, 18.05.2026-20.05.2026. doi: 10.5220/0015048600004021
Together, these research activities illustrate SAILeR's research-driven development approach: research is used not only to generate scientific knowledge, but also to inform the development of concepts and functionalities that can be implemented and evaluated in practice. Current and upcoming research will continue this approach through the development and evaluation of the AI assistant for learning design and further work on study programme learning design.