About

In modern education various information systems are used to support educational processes. In the majority of cases these systems have logging capabilities to audit and monitor the processes they support. At the level of a university, administrative information systems collect information about students, their enrolment in particular programs and courses, and performance like examination grades. In addition, the information about the lectures, instructors, study programs, courses and prerequisites, are typically available as well. These data can be analyzed from various levels and perspectives, showing different aspects of organization, and giving us more insight in the overall educational system. From the level of an individual course we can consider participation in lectures, accomplishing assignments, enrolling in midterm and final exams. However, with the development and increasing popularity of blended learning and e-learning, information systems enable us to capture activities also at different levels of granularity. Besides more traditional tasks like overall student performance or drop out prediction, it becomes possible to track how different learning resources (videolectures, handouts, wikis, hypermedia, quizzes) are used, how students progress with (software) project assignments (e.g. by analyzing svn commits), self-assessment test and questionnaires, etc.
In our research we work on adopting existing process mining and data mining approaches for solving various educational data mining tasks as well as developing new algorithms and techniques tailored to the educational domain with a particular focus on integrating domain knowledge in the mining process.
We mine educational data accumulated in different data sources including but not limited to administrative databases, learning manahement systems (LMSes) supporting blended and e-learning (or e-health), intelligent tutoring systems (ITS) and adaptive educational hypermedia (AEH) systems.
We are interested in developing an open source software package EduProM (on the top of the ProM) to make data and process mining easy for educators and other researcher working in EDM.
The main objective of CurriM pilot project funded by Surf is to help individual students (as well as educators), to get a holistic view on the study programs and to better understand the envisioned and monitor the actual educational process. Particular kinds of questions, for which we want to provide an automated support, include but are not limited to: “What are the recommended choices in the curriculum for me?”, “Why should I put attention to a particular course or prerequisites? How does a course relate to the program? Also with resect to its prerequisites and follow up dependencies?”, “Is my study plan compliant with the official curriculum (constraints)?”, “Am I on track, will I graduate successfully? in time? above average? with honors?”, “Should I take now courses A, B, C or C, D?”
10 questions and answers about CurriM can be found in this blog post. You may be interested in CurriM GUI demo. Surf maintains a webpage with the main info on CurriM pilot.
A couple of notes about CurriM have appeared in Surf magazine and in Netkwesties.nl. Surf prepared 14 min, 7 min, 2.5 min video summaries of learning analytics pilot projects funded by Surf.
Another interesting area we explore is stress analytics in education. Students are exposed to different kinds of stress, especially during the difficult studying periods like final exams weeks or project deadlines. We aim at providing means to students to become aware of the past, current and expected (objectively measured) stress and its correlation with their performance, to understand their stressors, to cope with and prevent stress - thus, to live healthier and happier lives and better organize their studies. You can read about this project idea from this short paper.
Collaborators
TU/eInternship and Master Students |
U. La Laguna, SpainU. Cordoba, Spain |
Events
- 6th International Educational Data Mining Conference (EDM 2013), Memphis, US
Future Events
- 4th International Educational Data Mining Conference (EDM 2011), Eindhoven, the Netherlands
- EDM Workshop @ 9th Int. Conf. on Intelligent Systems Design and Applications (ISDA'09), Pisa, Italy
- Applying Data Mining in e-Learning (ADML'07) Workshop @ ECTEL'07, Crete, Greece
- EDM Workshop @ ICALT'07, Niigata, Japan
Organized Events
- 2nd International Educational Data Mining Conference (EDM 2009), Cordoba, Spain
- 1st International Educational Data Mining Conference (EDM 2008), Montreal, Canada
Past Events
Publications
- Pechenizkiy M., Trcka N., De Bra P., Toledo P. CurriM: Curriculum Mining. EDM 2012: 216-217, [PDF]
- Calders T., Pechenizkiy M. Introduction to the special section on educational data mining. SIGKDD Explorations 13(2): 3-6 (2011), [PDF]
- Pechenizkiy M., Calders T., Conati C., Ventura S., Romero C., Stamper J. (Eds.): Proceedings of the 4th International Conference on Educational Data Mining, Eindhoven, The Netherlands, July 6-8, 2011. www.educationaldatamining.org 2011, isbn 978-90-386-2537-9
- Romero, C., Ventura, S., Pechenizkiy, M. & Baker, R. (Eds.) (2010) Handbook of Educational Data Mining, Chapman&Hall/CRC Data Mining and Knowledge Discovery Series, CRC Press, Taylor&Francis Group.
- Trčka, N., Pechenizkiy, M. & van der Aalst, W. (2010) "Process Mining from Educational Data", In Handbook of Educational Data Mining.
- Dekker, G., Pechenizkiy, M. & Vleeshouwers, J. (2009) Predicting Students Drop Out: a Case Study, In Proceedings of the 2nd International Conference on Educational Data Mining (EDM'09), pp. 41-50. [BIB] [PDF]. Extended version is available as an internship report.
- Trčka, N. & Pechenizkiy, M. (2009) From Local Patterns to Global Models: Towards Domain Driven Educational Process Mining, In Proceedings of Ninth International Conference on Intelligent Systems Design and Applications (ISDA'09), pp. 1114-1119. [BIB] [PDF]
- Pechenizkiy, M., Trčka, N., Vasilyeva, E., van der Aalst, W. & De Bra, P. (2009) Process Mining Online Assessment Data, In Proceedings of 2nd International Conference on Educational Data Mining (EDM'09), pp. 279-288. [BIB] [PDF]
- Pechenizkiy, M., Calders, T., Vasilyeva, E. & De Bra, P. (2008) Mining the Student Assessment Data: Lessons Drawn from a Small Scale Case Study, In Proceedings of the 2nd Conference on Educational Data Mining (EDM'08), pp. 187-191. [BIB] [PDF]
Presentations & posters
- Educational Data Mining & Learning Analytics for All: Potential, Dangers, Challenge. Learning Analytics Seminar, Utrecht, the Netherlands (August 2011)
- Learning with Actionable Attributes: Learning to Effectively Help Those Who Need Help. University of Sydney, Australia (December 2010)
- Towards EDM framework for Personalization of Information Services in RPM Systems. The 3rd International Conference on Educational Data Mining (poster@EDM’10)
- Predicting Students Drop Out: a Case Study, (EDM'09)
- Process Mining Online Assessment Data, (poster@EDM'09)
- From Local Patterns to Global Models: Towards Domain Driven Educational Process Mining, (EDM@ISDA'09)