Hybrid machine learning models for aspectbased sentiment analysis on MOOC Quora reviews for e-learning personalization

The growing popularity of Massive Open Online Courses (MOOCs) makes it hard for new learners to choose the right platform. To help with this, a web-based application was developed to analyse reviews from Quora using Aspect-Based Sentiment Analysis (ABSA). The system uses a special hybrid machine learning model that combines a Decision Tree (DT) and a Support Vector Machine (SVM) to sort user comments by sentiment and five key topics, including content, structure, assessment, interaction, and instructor. This combination of models makes the system more accurate and reliable. The application shows these results for Coursera, edX, and Udemy using easy-to-understand charts and gives recommendations. The hybrid model was effective, achieving an overall accuracy of 92% on the development data. This project offers a useful tool that helps students make smarter choices when picking a MOOC.