In educational settings concept maps are often chosen as a tool to help knowledge constructions be visualized. While mapping out concepts and their relationships, students are able to show how well (or not well) they understand certain subjects. A newly published study, which was presented at the AIED 2024 in Recife, Brazil, takes their usage a step further, examining the structural patterns in concept maps and developing an automated system to classify them.
The researchers categorized 511 different concept maps into three key structures: spoke, network and chain. Each structure type can provide its own insight about the deepness of students’ understanding. For example, a “spoke” structure may indicate a surface-level understanding, while a “network” might reflect a more complex comprehension.
The researchers trained multiclass classification models using statistical data and descriptive features from these maps. The most impressive model was a Random Forest model with 88% accuracy, which gives is especially promising for the future of educational assessment tools. With such a system, students could be given real-time feedback to help them improve their understanding of the subject matter.
All in all, this approach makes a promising step toward more effective and responsive concept map assessments, which can be a valuable asset for educators to better evaluate their students knowledge and help teach them in a more personalized manner.
Check out the paper for more details:
Vossen, L.P.V., Gasparini, I., Oliveira, E.H.T., Menzel, L., Gombert, S., Neumann, K. & Drachsler, H. (2024). Conceptual Map Assessment Through Structure Classification. In: L. Benedetto, A. Caines, G. Duenas, D. Galvan-Sosa, A. Loukina, S. Taslimipoor & T. Zesch (Eds.), EvalLAC 2024 Automated Evaluation of Learning and Assessment Content: Proceedings of the First Workshop on Automated Evaluation of Learning and Assessment Content co-located with the 25th International Conference on Artificial Intelligence in Education (AIED 2024) (Vol. vol 3772, pp. 1-7). online: CEUR Workshop Proceedings.