Professor of Computational Methods in Modeling and Analysis of Learning Processes
University of Duisburg-Essen
My name is Irene-Angelica Chounta and currently, I am a Professor in "Computational Methods in Modeling and Analysis of Learning Processes" at the Department of Human-centered Computing and Cognitive Science at the Faculty of Computer Science, University of Duisburg-Essen (UDE) in Germany. My research focuses on computational learning analytics for technology-enhanced learning, Artificial Intelligence in Education (AIED) and educational technologies. My main research interest is to model learners' behaviour in order to provide adaptive and personalized feedback, either in formal or informal contexts.
I was born and raised in Athens, Greece and I have lived and worked in Germany, Estonia, and the USA. I am an Executive Board Member of the International Artificial Intelligence in Education Society (IAIED), and a member of the International Society of the Learning Sciences (ISLS) and the European Association for Technology Enhanced Learning (EATEL).
I believe that education is the answer to many questions, along with kindness. I also believe in working together to achieve common goals. My overarching goal is to empower humans to aim for their dreams and beyond of what is "possible," and to use my privilege and power to provide opportunities and support those around me — especially youth from underrepresented groups and minorities. Everyone has a right to education.
At UDE, I lead the research group colaps, where we explore the use of computational data analytics, namely machine learning and data mining, with the aim to support learning from the perspective of personalization and adaptation, and in relation to tutoring feedback and scaffolding. You can find out more about colaps at uni-due.de/colaps.
Leading the research group colaps, exploring computational methods such as Artificial Intelligence, Learning Analytics and Data Mining to model how we learn in both formal and informal learning contexts.
Focused on computational methods for modeling and analysis of learning processes across intelligent learning environments, online learning, and project-based learning.
Used learning analytics to provide feedback and guidance to students and to scaffold learning, drawing on data from the university's Study Information System for teacher and student dashboards.
At the Human-Computer Interaction Institute in Pittsburgh, designed a student model evaluating understanding of a physics curriculum to adapt tutorial dialogues in content, style, and language.
Member of the COLLIDE research group, using learning analytics to analyze learning activities in computer-supported collaborative learning environments, online labs, and MOOCs.
Thesis on using learning analytics to assess collaboration quality in CSCL activities, proposing and implementing an automatic rater of collaboration quality via time series analysis.
Studied with an emphasis on electronics, processors, and computer architecture; diploma thesis proposed an information system for monitoring geographically distributed networks.
First higher academic degree, working with Prof. Sotiris Leventis on computer networks as a member of PeLAB.
Download Research Statement (PDF) →
Modeling when and how confidently a computational model can predict a student's behavior according to theories of learning, rather than the behavior alone, can reveal the moments that matter most for learning and intervention, pointing toward a broader potential for learning models that don't just track performance, but learn to recognize their own uncertainty as a signal for where and when to act (Chounta et al. 2017; Schulze Bernd & Chounta, 2022; Sheng & Chounta 2026; Chounta & Avouris, 2016; Chounta & Carvalho, 2019)
Exploring the ingtegration of AI in classrooms (Chounta et al., 2024), the impact of the use of AI on cognitive dimensions of AI in classrooms and the fair, and ethical use of AI in education (Chounta et al. 2022; Holmes et al, 2022) I argue that when we ask technical questions about AI in education, we need to connect them to the same human rights principles that already guide policy elsewhere. That way, policy keeps up with how these tools actually affect students' thinking, not just with what the technology can do.
While maker/hack scenarios are usually informal, extracurricular activities, their real value lies not in the final product but in the whole social process behind it, the knowledge-seeking, peer influence, self-reflection, and sharing, which suggests these competencies can be deliberately cultivated by bringing maker culture into the classroom and turning hackathons, devcamps, and makerspaces into structured learning opportunities (Schulten, Nolte & Chounta, 2027; Schulten & Chounta, 2023; Chounta, Manske & Hoppe, 2017).
The full list can be found at: Google Scholar Profile
Schulten, C., Nolte, A., & Chounta, I. A. (2027). HackEDX: Towards a methodological framework for Hackathons as educational experiences. Educational Technology & Society, 30(1), 196-212. [DOI]
Sheng, K., & Chounta, I. A. (2026). Beyond One-Size-Fits-All: Personalizing Computational Proxies of the Zone of Proximal Development Through Help-Seeking Behaviors. In Artificial Intelligence in Education (AIED 2026), LNCS vol. 16585. Springer, Cham. [DOI]
Chounta, I. A., Ortega-Arranz, A., Daskalaki, S., et al. (2024). Toward a data-informed framework for the assessment of digital readiness of higher education institutions. International Journal of Educational Technology in Higher Education, 21, 59. [DOI]
Schulten, C., & Chounta, I. A. (2024). How do we learn in and from Hackathons? A systematic literature review. Education and Information Technologies, 29, 20103-20134. [DOI]
Chounta, I. A., Limbu, B., & van der Heyden, L. (2024). Exploring the Methodological Contexts and Constraints of Research in Artificial Intelligence in Education. In Generative Intelligence and Intelligent Tutoring Systems (ITS 2024), LNCS vol. 14798. Springer, Cham. [DOI]
Schulze Bernd, N., & Chounta, I. A. (2024). Beyond the Grey Area: Exploring the Effectiveness of Scaffolding as a Learning Measure. In Artificial Intelligence in Education (AIED 2024), LNCS vol. 14829. Springer, Cham. [DOI]
Chounta, I. A., Bardone, E., Raudsep, A., et al. (2022). Exploring Teachers' Perceptions of Artificial Intelligence as a Tool to Support their Practice in Estonian K-12 Education. International Journal of Artificial Intelligence in Education, 32, 725-755. [DOI]
Holmes, W., Persson, J., Chounta, I. A., Wasson, B., & Dimitrova, V. (2022). Artificial intelligence and education: A critical view through the lens of human rights, democracy and the rule of law. Council of Europe.
Chounta, I. A., & Carvalho, P. F. (2019). Square it up! How to model step duration when predicting student performance. In Proceedings of the 9th International Conference on Learning Analytics & Knowledge (LAK19), pp. 330-334. ACM. [DOI]
Chounta, I. A., Manske, S., & Hoppe, H. U. (2017). "From Making to Learning": introducing Dev Camps as an educational paradigm for Re-inventing Problem-based Learning. International Journal of Educational Technology in Higher Education, 14, 21. [DOI]
Chounta, I. A., Albacete, P., Jordan, P., Katz, S., & McLaren, B. M. (2017). The "Grey Area": A Computational Approach to Model the Zone of Proximal Development. In Data Driven Approaches in Digital Education (EC-TEL 2017), LNCS vol. 10474. Springer, Cham. [DOI]
Chounta, I. A., & Avouris, N. (2016). Towards the real-time evaluation of collaborative activities: Integration of an automatic rater of collaboration quality in the classroom from the teacher's perspective. Education and Information Technologies, 21, 815-835. [DOI]
The Moral Underpinnings of Disinformation Acceptance in Human-AI-Interaction: The Case of Moral Alignment.
An integrated framework for delivering educational hackathons to support creativity and entrepreneurship in Higher Education Institutions.
Ethical and Inclusive AI for Higher Education.
Augmented Intelligence for Pedagogically Sustained Training and Education.
Digital Readiness in European Higher Education Institutions: a Data-driven Framework Guided by Institutional and Instructional Analytics.
Combining Machine-learning and Learning Analytics to provide personalized scaffolding for computer-supported learning activities. Estonian Research Council, grant PSG286.
In my courses, my aim is to support students in acquiring much-needed skills for the 21st-century learner, such as critical thinking, problem-solving, and data literacy. I follow a project-based learning approach where each student carries out a small project with and through technology, following a design–implementation–evaluation iterative process, and I combine formal lectures with hands-on workshops to foster communication and knowledge-building on common ground.
Download Teaching Statement (PDF) →Happy to hear from prospective students, collaborators, and anyone thinking about learner modeling.