:async: Personalized Recommendation Based on Learning Analytics in MOOC Environment

Authors: Nen-Fu Huang, Jian-Wei Tzeng, Chia-An Lee, An-Chi Chuang, Yi-Hsien Chen
Institutions: Department of Computer Science, National Tsing Hua University, Center for Teaching and Learning Development, National Tsing Hua University
Country: Taiwan

Topic: Innovation through MOOCs practices
Sector: Higher Education
UNESCO Area of Focus: Sustainable OER
Session Format: Presentation


The rapid development of Massive open online courses (MOOCs) in recent years has enabled users from all over the world to increase their chances to learn online without being affected by the region and without time constraints. However, a lot of learners still cannot complete the course because of their stress-free learning environment, learners often can not complete the whole courses. Due to enormous amount of learning materials in various learning environments, learners also have difficulties in searching what they need on MOOCs. In addition, when students encounter difficulties in the course of learning, they also need an assistant role who can be able to provide learning strategies as well as knowledge and message management. Therefore, these problems led us to think on the way to help learners not to be lost. Recommendation systems(RS), which are applied in education, can play a major role for supporting educational practices. The main objective of recommender systems is to provide custom resources and relevant learning materials based on the needs for students to maximize their performance. Consequently, how to integrate the recommendation system with MOOCs to provide personalized recommendations to the learners is one of the hot issues. In this study, we proposed a MOOC Intelligent Recommendation System(MIRS) based on learning diagnosis, learning clustering, aiming at providing more precise personalized recommendation. We will also construct the heat-map system through the common learning time of each student, it can be analyzed to become a proper time, and finally proper recommendation timing will be given by the heat-map system. The system will then provide learning materials like related course videos or exercises for each student, giving guidance to students for much better understanding of course contents. The proposed system can not only help the students improve their learning but also adjust their learning accordingly.


Massive open online course, learning diagnosis, learning cluster, recommendation system

1 Like