Discovery and Recommendation of First-Hand Learning Resources Based on Public Opinion Cluster Analysis

Authors

  • Haiyun Li South China Normal University
  • Xuebo Zhang South China Normal University
  • Junhui Wang South China Normal University

DOI:

https://doi.org/10.3991/ijet.v12i12.7965

Keywords:

personalized learning recommender, public opinion, text clustering

Abstract


This paper explores the personalized approach of the public opinion cluster analysis for learning resources based on the server-side predetermined analysis, in order to introduce the personalized learning resource recommender into the traditional online instruction. In allusion to further validation on its implementation, the fuzzy aggregation of learning resources is mined up based on the proposed WRTC algorithm. The personalized learning resource recommender mechanism is then described. In the end, the common evaluation parameters in the personalized recommender model are applied in the evaluation on the system performance. The experiment is carried out with learner's access data online to validate whether the algorithm and the model indicators are effective for the purpose of improving the precision and coverage of learning resources.

Author Biographies

Haiyun Li, South China Normal University

Haiyun Li is from South China Normal University.

Xuebo Zhang, South China Normal University

Xuebo Zhang is from South China Normal University.

Junhui Wang, South China Normal University

Junhui Wang is from South China Normal University.

Downloads

Published

2017-12-20

How to Cite

Li, H., Zhang, X., & Wang, J. (2017). Discovery and Recommendation of First-Hand Learning Resources Based on Public Opinion Cluster Analysis. International Journal of Emerging Technologies in Learning (iJET), 12(12), pp. 112–118. https://doi.org/10.3991/ijet.v12i12.7965

Issue

Section

Short Papers