Funded Projects

augMentor aims to develop a novel pedagogical framework that promotes basic skills and 21st century competencies by integrating emerging technologies.
The development of personalized and collaborative learning and the achievement of higher-order thinking skills – the so-called 21st century competencies – is still nowadays a significant challenge. At the same time, it is of great interest to understand how learners work, how educators orchestrate their classrooms, and what information they have access to in order to adapt/enhance/improve their orchestration.
Emerging technologies have the potential to propel the change from an instructional teaching paradigm, that favors mass instruction, to a learner-centered paradigm, that promotes the development of new roles for both the teacher and the learner. However, their acceptability and adoption are still slow mainly due to fragmented approaches. Importantly, in order to ensure quality education it is mandatory to address unexpected emergencies and disruptive events that may undermine the human and social dimensions of learning.
augMENTOR adopts an augmented intelligence approach, where people and machines work together, building on their own strengths, to develop customized and collaborative learning paths that promote both basic and 21st century competencies as well as design thinking and creativity. augMENTOR will leverage advancements in the fields of Pedagogical Design, Creative Pedagogy, Explainable Artificial Intelligence, and Knowledge Representation and Reasoning for instructional purposes.

One of the challenges novice programmers face when practicing code-writing is interpreting and addressing compiler and interpreter warnings and error messages (Becker et al., 2019). This may explain why popular interactive programming environments like Jupyter Notebooks have not caught up with teaching introductory programming in HE (Al-Gahmi et al., 2022) despite their popularity and envisioned potential (Ramírez-Echeverry et al., 2022). Additionally, systems used for code-writing – including Jupyter Notebooks – do not provide instructional support such as worked examples, or supplementary materials that could help students interpret and work with compiler error messages, and understand what a program does or why it does not do what was intended. However, studies in our classes show that such materials and clear communication of expected learning outcomes have a positive effect on the achieved outcomes (Mauritz et al., 2022).
This project aims to answer two research questions as a first step to address this challenge:
- RQ1: What is the optimal prompting condition in order to have an LLM generate hints that best help students understand and learn from compiler errors?
- RQ2: How can we help students with exhibiting prompting behavior that leads to optimal tailored feedback/support from the LLM model?
Completed Projects
- DigiReady+: A Higher Education Framework for measuring digital readiness, 2022-2025, https://digiready.eu