New Personalized Recommendation System for E-Learning
AshEse Journal of Physical Science
Vol. 5(5), pp. 063-067, August, 2021
ISSN: 2059-7827
© 2021 AshEse Visionary Limited
http://www.ashese.co.uk/physical-science1/blog
Full Length Research
New Personalized Recommendation System for E-Learning
S. Bhaskaran and Raja Marappan*
School of Computing, SASTRA Deemed University, Thanjavur, India
*Corresponding author. E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
Received August, 2021; Accepted August, 2021
Customized E-learning dependent on the recommender framework is perceived as one of the most interesting investigations in the field of education. Most of the researchers designed a various recommender e-learning approach which utilizes recommendation techniques for educational data mining specifically for identifying e-learners’ learning preferences. However, it does not provide satisfactory results.To increase the recommendation accuracy and minimize the query processing time, the proposed system designed a new personalized recommendation. Initially the learning styles of learners are taken out from server blogs. After the completion of preprocessing, similarity computation and recommendations are done. First, the system applies the content-based filtering approach to calculate the recommendation list. The outcomes are ranked depends on the adjusted cosine similarity of their content. Then apply a collaborative approach to categorize the active learner in one of the learner’s groups. The investigational outcomes show that the designed scheme attains higher performance matched with the previous system in terms of query processing time, MAE and accuracy.
Key words: Vector space model, recommendation system, adjusted cosine, document frequency.