Prediction of learners’ learning styles in online environments has several advantages, including steering learners on the proper path, motivating and engaging them while learning, and improving their learning results. It also helps instructors in the formation of personalized resource recommendations. As a result, predicting learners learning styles is necessary to aid in the personalization process. Existing approaches use either conventional or automatic approaches for learning style identifications. However, the large volume of data stored in online platforms has become a challenge in analyzing the behavior of learners and predicting their learning styles in the real world. Also, most of the existing approaches rely on a particular learning platform and can not be used in other platforms without technical assistance. In this paper, we propose GNN-LS, a new approach to identify and predict learners learning styles using a graph neural network. First, the graph embedding technique is used to capture the representation of learners and resources as a bipartite graph and encode them into low-dimensional representation. The encoded L-R sequences were given as input to the K-means clustering algorithm to identify and obtain labels as per FSLSM dimensions. Then, Graph neural network is trained to predict the learner’s learning style in the real world. The GNN-LS technique can be applied in a variety of educational systems and adapted to fit a variety of learning style models. Extensive experiments are run using the 2015 KDD Cup public available dataset to demonstrate the capabilities of GNN-LS. 5.31-15.68% improvements are achieved across all four FSLSM dimensions in accuracy.

The ability to detect learners’ learning styles based on their learning behaviors is of utmost importance for online educational systems, as it greatly enhances student engagement, motivation, and overall learning outcomes. Knowing the learning preferences of learners may significantly aid in creating personalized learning recommendations and empower learners to identify their own learning styles. However, learners exhibit diverse behaviors in an online setting, which poses significant difficulties in detecting their learning style. This paper proposes a novel approach for detecting learning styles using graph representation learning techniques and machine learning algorithms. While our approach is not reliant on a particular learning style model, our approach may be divided into two distinct parts. Initially, we represented the behavior of learners as a bipartite graph and then transformed this graph into a lower-dimensional representation using the graph embedding approach. This lower-dimensional representation was then utilized for machine learning tasks. Furthermore, we categorize the encoded learner’s sequence using a clustering technique based on the selected learning style model. Our methodology uses the Felder-Silverman model as the learning style model and the Fuzzy C-means algorithm as a clustering technique. Our approach was evaluated using the 2015 KDD Cup dataset through a series of comprehensive experiments to showcase its effectiveness. The findings demonstrate that our approach surpasses the previous approach, achieving an average precision of 0.8737 and an accuracy of 0.9182.

Online learning has become increasingly popular in recent years. This interest in online education has provided us with many opportunities to research, the behavior of learners as it generates behavior data at large scale. By dynamically adapting learning, the automated identification of learning styles in online learning based on learner activity is a significant issue, in which many researchers have shown their interests as it improves learning output. In this paper, the collection of behavioral characteristics, which is an important step in the automated extraction of learning styles has been considered. We propose a conceptual framework for the identification of learning styles that automatically learns features from the context of online education through graph representation learning. We used the learned features and mapping rules to distinguish learning styles in the Felder-Silverman learning style theory. The alternative approach is expected to provide a better outcome, a more reliable identification of learning style than the previous processes. Future research directions are provided in the study.