Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{207439,
        author = {Harshitha G and Monisha M and Sujay S},
        title = {EduGuide: A Hybrid NLP-Driven Course Recommendation System for Personalized Online Learning Using TF-IDF and Machine Learning Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {3},
        pages = {1327-1333},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=207439},
        abstract = {This study presents the development and evaluation of a Hybrid Course Recommendation System using NLP and Machine Learning techniques to assist learners in identifying relevant online courses from large educational platforms.To fill these gaps,this work proposes a hybrid course recommendation system,which combines the machine learning and Natural Language Processing(NLP) techniques to deliver personalized course recommendations from large scale educational platforms.Course descrip-tions are processed in a structured pipeline of text processing which includes tokenization,stopword removal and lemmatization to get more readable and clear representation of course content.To know the similarity between a course and interest of a learner these descriptions are converted to numerical form by using TF-IDF vectorization and cosine similarity is used.We employ a hybrid scoring system that combines course ratings and similarity scores in a balanced way to further improve the output,considering both quality and rel-evance.
Many experiments were performed on dataset gathered from Coursera which contains course descriptions,difficulty level,institutional affiliation,skill tags and learner ratings.The system’s has the capability in recommending relevant courses across different domains which include A1,Data Science,Machine Learning and Web development.The recommendations are also presented visually,which aloows end users to understand the scores more easily.The whole system is lightweight and scalable and a useful tool for individual educational advice.Future directions for improving recommendations include combination of collaborative filtering with deep learning architectures and the integration of real-time feedback.},
        keywords = {},
        month = {August},
        }