Descoberta de padrões de engajamento em MOOCs através de análise de agrupamento (Discovery engagement patterns MOOCs through cluster analysis)

Rodrigo Lins Rodrigues (, Jorge Luis Cavalcanti Ramos (, João Carlos Sedraz Silva (, Alex Sandro Gomes (

1Universidade Federal Rural de Pernambuco
2Universidade Federal do Vale do São Francisco
3Universidade Federal de Pernambuco

This paper appears in: Revista IEEE América Latina

Publication Date: Sept. 2016
Volume: 14,   Issue: 9 
ISSN: 1548-0992

Cluster analysis can be used to help researchers identify behavioral patterns of students with regard to engaging in interactions via the forum and during activities during a course in MOOC mode (English, Massive Open Online Course). This article aims to analyze the effectiveness of educational data mining techniques, specifically the cluster analysis to identify students engagement patterns in MOOC courses in mode. The analyzes in this article demonstrate the use of hierarchical clustering method (Ward clustering) and the non-hierarchical clustering method (k-means) to analyze the engagement behavior characteristics, involving carrying out activities and interactions via the forum. For the analysis were taken into account the interaction patterns made in discussion murals in Openredu platform, as well as data access and activities of completeness. The insights found in this study can serve as indications for use by MOOCs designers to meet the diversity of engagement patterns and design interfaces that guide the design of adaptive strategies that allow increasing engagement and fostering a better learning experience.

Index Terms:
Educational Data Mining, EDM, Clustering Hierarchical method, Clustering Non-hierarchical method   

Documents that cite this document
This function is not implemented yet.

[PDF Full-Text (311)]