publications

2026

1. ANVIL: Analogies and Videos for Lecturers

   Yuri Noviello, Anastasiia Birillo, and Gosia Migut

   In Artificial Intelligence in Education: 27th International Conference, AIED 2026, Seoul, South Korea, June 27–July 3, 2026, Proceedings, Part I, Seoul, Korea (Republic of), 2026

   Abs DOI

   We present ANVIL, a multimodal generative system that automates the production of analogy-based instructional animations for computer science topics. Given a concept definition, ANVIL generates a textual analogy, compiles it into a structured visual screenplay, and produces executable manim code to render an animation, with an automated repair mechanism to improve robustness. Evaluating such systems at scale requires balancing pedagogical validity with scalability. We begin with a teacher evaluation to ground the quality assessment and use its findings to guide automated screening. For textual analogies, we introduce an LLM-based evaluator for scalable quality screening; for videos, where subjective judgments are difficult to automate, we instead assess fidelity to the intended screenplay using an automated proxy for auditing and error analysis. We further conduct a user study with educators to examine adoption requirements and risks. Our findings suggest that ANVIL can produce materials that are frequently rated as adequate, and that educators respond positively to its perceived value and usability.

2. From Students Struggles to Teachers Insights: A Dashboard of Student-AI Interactions in ML Practical Assignments

   Boyun Zhang, Ilinca Rentea, and Gosia Migut

   In Proceedings of the 31st ACM Conference on Innovation and Technology in Computer Science Education V. 2, Spain, 2026

   Abs DOI

   When students work on self-paced, unsupervised practical assignments in Machine Learning courses, teachers have little visibility into the difficulties students encounter. In our Machine Learning course, students completed a practical assignment using JELAI, an AI-supported programming environment. The recorded student-AI interactions were classified into pedagogically meaningful categories and visualized in a teacher-facing dashboard. An initial evaluation showed that teachers found the dashboard useful, while also identifying areas for improvement. We describe our experience and discuss the potential and challenges of using student-AI interactions to improve teaching practice.

3. AI-Generated Traces for Novice Programmers: Learning Effects and Learner Differences in a Multi-Institutional Study

   Yuri Noviello, Naaz Sibia, Anastasiia Birillo, Thomas Overklift Vaupel Klein, Michael Liut, and Gosia Migut

   In Proceedings of the 31st ACM Conference on Innovation and Technology in Computer Science Education V. 1, Spain, 2026

   Abs DOI

   Introductory programming (CS1) courses often struggle to support students’ understanding of program execution. While visualizations can make execution processes explicit, their effectiveness depends on design and context, and empirical evidence for AI-generated visualizations remains limited. We propose Generated Animated Traces (GATs), AI-generated, analogy-based, narrated animations that coordinate source code, execution state, and conceptual analogies. We conduct a study at two institutions in CS1 courses (Python N=961; Java N=151) comparing GATs to textual explanations. We measure immediate learning performance and experience, end-of-course engagement and exam performance. Results show that GATs can yield selective benefits for immediate learning, but benefits are context-dependent and short-term. We observe that GATs’ influence on performance is moderated by learner engagement profiles. This finding underscores the importance of personalized approaches.

4. Proposing Threshold Concepts in Machine Learning

   Lisa Zhang, Gosia Migut, and Jesse H. Krijthe

   In Proceedings of the 31st ACM Conference on Innovation and Technology in Computer Science Education V. 1, Spain, 2026

   Abs DOI Blog

   Machine learning (ML) courses are difficult to design and teach for many reasons: new approaches emerge rapidly, and students are already overwhelmed with the volume of material. This position paper addresses the question of what is essential to teach in ML courses through the framework of threshold concepts—transformative ways of understanding that fundamentally shift how learners view a discipline. We propose five threshold concepts in ML: ”Learning is Optimization,” ”There are Tradeoffs in Sources of Error,” ”ML is an Empirical Science,” ”ML Describes Geometric Processes,” and ”ML Demands a Probabilistic Lens.” We believe the first three concepts to be essential for students aiming to become adept builders of ML systems, and the remaining two to be necessary for graduate-level research in developing new ML methods. For each concept, we analyze whether and how it is transformative, troublesome, integrative, irreversible, and bounded. These concepts are intentionally chosen to be broad and model-agnostic, so that they can be applied to a wide range of settings and remain relevant as the field progresses. Our proposals reflect the reasoned analysis of experienced ML educators and offer a learner-centered framework for prioritizing limited instructional time while helping students develop a deeper understanding of ML. Furthermore, we contribute to the ongoing conversation about the role of mathematics in ML education by arguing that mathematics is necessary for the two theoretical concepts and for moving beyond mimicry to true understanding through the liminal space of threshold concepts.

2025

1. Unveiling cognitive processes in digital reading through behavioural cues: A hybrid intelligence (HI) approach

   Y Lee, G Migut, and M Specht

   British Journal of Educational Technology, 2025
2. Multimodal Analogy Generation in Programming Education

   Y Noviello, A Birillo, and G Migut

   In Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education, 2025
3. Are Interactive Visualizations in Machine Learning Education Helping Students?

   I Rentea, G Migut, and J Krijthe

   In Proceedings of the 30th ACM Conference on Innovation and Technology in Computer Science Education, 2025
4. Creating in-IDE Programming Courses

   A Birillo, H Keuning, G Migut, K Dzialets, and Y Golubev

   In Proceedings of the 56th ACM Technical Symposium on Computer Science Education, 2025
5. The Research Project in Computer Science Bachelor Education: Undergraduate Research Experience at Scale

   G Migut, A Buszydlik, and MM Weerdt

   2025

2023

1. What attention regulation behaviors tell us about learners in e-reading?: Adaptive data-driven persona development and application based on unsupervised learning

   Y Lee, G Migut, and M Specht

   IEEE Access, 2023
2. Behavior-based feedback loop for attentive e-reading (bflae): A real-time computer vision approach

   Y Lee, MA Migut, and MM Specht

   In , 2023

2021

1. ReproducedPapers.org: Openly teaching and structuring machine learning reproducibility

   B Yildiz, H Hung, JH Krijthe, CCS Liem, M Loog, G Migut, FA Oliehoek, and others

   In International Workshop on Reproducible Research in Pattern Recognition, 2021

2020

1. Are we consistent? The effects of digitized exams grading

   G Migut and R Wiersma

   In Proceedings of the 51st ACM Technical Symposium on Computer Science Education, 2020

2018

1. Cheat me not: Automated proctoring of digital exams on bring-your-own-device

   G Migut, D Koelma, CGM Snoek, and N Brouwer

   In Proceedings of the 23rd Annual ACM Conference on Innovation and Technology in Computer Science Education, 2018

2016

1. Features vs Prototypes: Amplifying Cognition with Common Data Graphics

   MA Migut and M Worring

   In EuroVis (Posters), 2016

2015

1. Visualizing multi-dimensional decision boundaries in 2D

   MA Migut, M Worring, and CJ Veenman

   Data Mining and Knowledge Discovery, 2015

2012

1. Visual exploration of classification models for various data types in risk assessment

   M Migut and M Worring

   Information Visualization, 2012
2. VAST Challenge 2012: Interactively finding anomalies in geo-temporal multivariate data

   G Migut, J Wees, D Bakker, B Goede, H Steltenphol, and others

   In 2012 IEEE Conference on Visual Analytics Science and Technology (VAST), 2012

2011

1. Interactive decision making using dissimilarity to visually represented prototypes

   MA Migut, JC Gemert, and M Worring

   In 2011 IEEE Conference on Visual Analytics Science and Technology (VAST), 2011

2010

1. Visual exploration of classification models for risk assessment

   M Migut and M Worring

   In 2010 IEEE Symposium on Visual Analytics Science and Technology, 2010