The rapid proliferation of online educational content has created an overwhelming challenge for learners navigating thousands of courses across the internet. Identifying the right course that aligns with an individual's existing skills, career aspirations, and personal interests is no longer trivial. This paper presents an intelligent learning recommendation framework that combines machine learning techniques with a full-featured web application to deliver personalized, real-time course recommendations. The platform implements a recommendation engine powered by Term Frequency-Inverse Document Frequency (TF-IDF) vectorization and cosine similarity computation using Scikit-learn. By analyzing a student's stated interests, career goals, and current skill set, the engine computes semantic similarity scores between the learner's profile and available courses, returning the most relevant recommendations. Beyond course recommendations, the platform incorporates an AI-driven career path prediction module that evaluates the learner's skill profile against predefined career personas-including Data Scientist, Full Stack Developer, Cloud Architect, Cybersecurity Analyst, and AI Engineer-and identifies the most suitable career trajectory with percentage-based match scores. A skill gap analysis module identifies specific skills the learner needs to acquire for their target career, directly linking gaps to relevant courses. The platform also includes a sentiment analysis module that classifies course reviews asPositive, Negative, or Neutral using keyword scoring.The complete system is built using Django 5.2, Bootstrap 5, and SQLite, providing user authentication, profile management, course enrollment tracking, and a responsive web interface.
Singh et al. (Thu,) studied this question.