Preliminary evidence on machine learning approaches for clusterizing students’ cognitive profile

Abstract

Assessing the cognitive abilities of students in academic contexts can provide valuable insights for teachers to identify their cognitive profile and create personalized teaching strategies. While numerous studies have demonstrated promising outcomes in clustering students based on their cognitive profiles, effective comparisons between various clustering methods are lacking in the current literature.In this study, we aim to compare the effectiveness of two clustering techniques to group students based on their cognitive abilities including general intelligence, attention, visual perception, working memory, and phonological awareness. 292 students, aged 11–15 years, participated in the study.A two-level approach based on the joint use of Kohonen's Self-Organizing Map (SOMs) and k-means clustering algorithm was compared with an approach based on the k-means clustering algorithm only. The resulting profiles were then predicted via AdaBoost and ANN supervised algorithms.The results showed that the two-level approach provides the best solution for this problem while the ANN algorithm was the winner in the classification problem.These results laying the foundations for developing a useful instrument for predicting the students’ cognitive profile.

Keywords

• Machine learning
• Self-organizing maps
• Cognitive profiling
• Specific learning difficulties (SLD)
• K-means