AdaptiLearn: real-time personalized course recommendation system using whale optimized recurrent neural network

In the modern world, the demand for personalized and efficient educational resources has increased significantly. Moreover, the rapid growth of online education platforms has made it difficult for learners to find the most relevant courses, which match their preferences and learning objectives. In this study, we aim to develop a cutting-edge browser extension for offering real-time course recommendations based on the users’ preferences. The proposed work combines advanced web scraping techniques with the optimized hybrid recommendation approach. The developed browser extension utilizes Streamlit a Python-based library for automating web interactions, enabling it to adapt to variations in website structures effectively. The proposed system combines the strengths of Collaborative and Content-based Filtering, utilizing the Whale Optimization and Recurrent Neural Network approach (WA-RNN). This optimized hybrid methodology ensures that recommendations are both personalized to user preferences and related to the content of the courses. Furthermore, the developed system incorporates a user feedback mechanism to continuously refine and improve the recommendation process. The proposed hybrid combination outclassed the existing techniques with a 0.3-s response time, 98% accuracy, 97.50% precision, 96.85% recall, 97.22% F-measure, and 0.45% MAE.