Author Affiliations
[1] Assistant Professor, Department of CSE, Er. Perumal Manimekalai College of Engineering, Hosur-635117, Anna University.
[2] [3] [4] Student, Department of CSE, Er. Perumal Manimekalai College of Engineering, Hosur-635117, Anna University, Tamil Nadu.
Abstract
In this information era, the rapid growth of online learning platforms has created an overwhelming number of MOOC courses, making it increasingly difficult for learners to select the most suitable ones for their career goals. This research proposes an Optimize Hybrid Intelligent MOOC Recommendation System that leverages advanced natural language processing and deep learning techniques to deliver highly personalized course recommendations. The system integrates the BB-OAM model combining BERT contextual embeddings, BiLSTM sequential modeling, and an Orthogonal Attention Mechanism to analyze learner sentiments and course reviews with 91.4% classification accuracy. The study employed a descriptive approach using 40,114 MOOC reviews. The ANOVA test results revealed that learners have strong awareness of MOOC platforms but face challenges in effectively utilizing smart recommendation features and understanding the usefulness of intelligent career-aligned course suggestions.
Keywords: MOOC Recommendation System, Sentiment Analysis, BB-OAM, BERT, BiLSTM, Orthogonal Attention Mechanism, Netlify Deployment, Career Guidance, Topic Modeling, Personalized Learning.
How to Cite This Article
T. Kanchana, S. Agalya, L. Charulatha, A. Kasthuri (2026). Optimize Hybrid Intelligent MOOC Recommendation System. International Journal of Innovative Research in Multidisciplinary Education & Technology (IJIRMET), 11(3).