Course Material Recommendation System for Slow Learner Students by Using Machine Learning Based on Learning Behavior and Course Material Complexity Score

Education data mining refers to the process of analyzing and extracting valuable insights from large datasets generated within the field of education. It involves applying data mining techniques, such as statistical analysis, machine learning, and predictive modeling, to educational data to uncover patterns, trends, and relationships that can inform educational practices and decision-making. Course material recommendation using machine learning involves leveraging machine learning algorithms to analyze user preferences, historical data, and content features to provide personalized recommendations for educational resources, such as textbooks, articles, videos, or online courses. Regular updates, feedback loops, and continuous monitoring are essential to maintain and improve the recommendation system's effectiveness. This paper focus onthree key aspects, first to identify the student learning behavior. We propose clustering method for the study of students' learning behavior associated with positive and negative outcomes (in exams). Second, is to introduce an approach to classifying student characteristics to predict performance on assessments data. We demonstrate that employing supervised classifiers results in a considerable improvement in classification performance. Finally, the study turns toward developing a technique for recommending appropriate study material by calculating readiness of student and complexity of course material. To achieve the objectives three models are proposed and combined into one for designing accurate and efficient course material recommendation model. In initial steps popular machine learning algorithmsi.e.K-Means, FCM (Fuzzy C Means), and K-FCM (kernel based FCM) is implemented to cluster students according to their learning behaviors. On the other hand, to designs a model for student performance prediction two supervised classifiers i.e. C4.5 and CART is implemented. Using both the components a course study material recommendation model is proposed. Further,for the final course material recommendations process syllabus of the UG course is used and the syllabus keywords are extracted. These keywords are used as query to find content from the internet. The identified material is offloaded and then preprocessing of the contents is carried out. The aim is to recover two kinds of features, first by using the NLP (natural language processing) based text parser to compute the material's complexity score. Second feature is calculated using TF-IDF as the content features. The calculated features are working as transaction set for Apriori algorithm. The Apriori algorithm is used for the frequent pattern mining. The obtained contents from this mining help to filter the data according to their content relevance. Secondly the complexity score of the document is used for suggesting the suitable course study material according to student's readiness compatibility. The experimental evaluation of the proposed ML based EDM framework demonstrate effectiveness, for supporting students to getting performance feedback, to enhance their learning, and obtaining relevant and personalized study material. The performance analysis in terms of precision, recall and F-score demonstrate the accurate outcomes of the recommendation model.