Machine Learning based Learning Style Detection using Felder-Silverman Framework

This research paper examines how the Felder and Silverman learning style framework can be used to predict student performance and improve learning outcomes by predicting a learner’s preferred learning style. By using a questionnaire-based approach, data can be collected and analyzed to categorize learners according to four dimensions: perception vs. intuitive; visual vs. visual; verbal vs. reflective; and sequential vs global. The predicted learning style information can then be used by educators to customize teaching strategies or course materials to meet the individual learning needs of learners, especially in online or distance learning settings. The adaptive approach has been shown to improve student engagement and learning outcomes. This framework is a valuable tool for understanding and responding to the diverse learning needs of students in different educational settings.