Multi-Label Classification and Explanation Methods for Students' Learning Style Prediction and Interpretation

Featured Application As students are usually characterized by more than one learning style, multi-label classification methods may be applied for the diagnosis of a composite students' learning style, based on each learner's activities in the virtual learning environment. For data sets with weakly correlated learning activities, Shapley values present the explanations for the predicted student's multi-label learning style. In this way, the model assists teachers in better understanding the cognitive traits of the learners in terms of learning activities, enabling teachers to prepare the relevant learning objects for the personalization of virtual learning environments. The current paper attempts to describe the methodology guiding researchers on how to use a combination of machine learning methods and cognitive-behavioral approaches to realize the automatic prediction of a learner's preferences for the various types of learning objects and learning activities that may be offered in an adaptive learning environment. Generative as well as discriminative machine learning methods may be applied to the classification of students' learning styles, based on the student's historical activities in the e-learning process. This paper focuses on the discriminative models that try to learn which input activities of the student(s) will correlate with a particular learning style, discriminating among the inputs. This paper also investigates several interpretability approaches that may be applicable for the multi-label models trained on non-correlated and partially correlated data. The investigated methods and approaches are combined in a consistent procedure that can be used in practical learning personalization.

Automated summary

This paper discusses the use of multi-label classification methods and machine learning techniques in combination with cognitive-behavioral approaches to predict learners' preferences. By analyzing students' activities in virtual learning environments, teachers can gain insights into cognitive traits and personalize the learning experience accordingly.