No Detail Found!

Course recommendation, exploratory data analysis and visualizations of massive open online courses (MOOCS)

Author(s)
Noman Islam Karachi Institute of Economics and, Technology,Karachi,Pakistan
Abdul Rafay Khan NED University of Engineering and NED University of Engineering and, Technology Technology,Karachi, Pakistan
Umair Ahmed NED University of Engineering and Technology Karachi, Pakistan
Ahmed Jaffer NED University of Engineering and Technology Karachi, Pakistan
Shamim Akhtar College of Applied Medical Sciences, Majmaah University AL-Majmaah, Saudi Arabia
Abstract
Users and learners nowadays are seeking their education on online platforms such as Open edX, Udemy, Udacity, and Coursera. However, online learners are faced with cumbersome tasks and various challenges to search for the required courses matching their individual goals, knowledge, and interest. With the huge amount of data and material available over the internet for MOOCs, users often face the difficulty of making the right decision to choose the right course that perfectly defines their interest and fulfills their learning requirements. Hence, the lack of targeted recommendations for MOOCs can drive users to choose irrelevant MOOCs. Recommender System (RS) plays a crucial role in assisting learners to find appropriate MOOCs to improve learners' engagements and their satisfaction/completion rates on the courses that satisfy their learning requirements. Basically, the aim is to visualize the student's areas of interest, which should not differ from the course recommendation and the overall structure of the course.
Publication Details
Page(s) 72-85
Published Journal: Journal of Independent Studies and Research Computing, Volume: 20, Issue: 1, Year: 2022

Request the full text from PASTIC

Keywords
Recommendation Systems, Collaborative Filtering, MOOCs, exploratory data analysis
0

Citations

0

Downloads

57

Views