On the Discovery of Educational Patterns using Biclustering

The world-wide drive for academic excellence is placing new requirements on educational data analysis, triggering the need to find less-trivial educational patterns in non-identically distributed data with noise, missing values and non-constant relations. Biclustering, the discovery of a subset of objects (whether students, teachers, researchers, courses and degrees) correlated on a subset of attributes (performance indicators), has unique properties of interest thus being positioned to satisfy the aforementioned needs. Despite its relevance, the potentialities of applying biclustering in the educational domain remain unexplored. This work proposes a structured view on how to apply biclustering to comprehensively explore educational data, with a focus on how to guarantee actionable, robust and statistically significant results. The gathered results from student performance data confirm the relevance of biclustering educational data.

[1]  Zachary A. Pardos,et al.  Co-Clustering by Bipartite Spectral Graph Partitioning for Out-of-Tutor Prediction , 2012, EDM.

[2]  Arlindo L. Oliveira,et al.  Biclustering algorithms for biological data analysis: a survey , 2004, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[3]  Zachary A. Pardos,et al.  Spectral Clustering in Educational Data Mining , 2011, EDM.

[4]  Mohamed Ben Ahmed,et al.  Simultaneous Clustering: A Survey , 2011, PReMI.

[5]  Cláudia Antunes.  Acquiring Background Knowledge for Intelligent Tutoring Systems , 2008, EDM.

[6]  Ryan S. Baker,et al.  Educational Data Mining and Learning Analytics , 2014 .

[7]  Antonio L. Furtado,et al.  An Analysis of Degree Curricula through Mining Student Records , 2017, 2017 IEEE 17th International Conference on Advanced Learning Technologies (ICALT).

[8]  Cláudia Antunes,et al.  Mining coherent evolution patterns in education through biclustering , 2014, EDM.

[9]  Mehmet Deveci,et al.  A comparative analysis of biclustering algorithms for gene expression data , 2013, Briefings Bioinform..

[10]  Rui Henriques,et al.  BicPAMS: software for biological data analysis with pattern-based biclustering , 2017, BMC Bioinformatics.

[11]  Ismail M.A,et al.  Clustering Algorithms Applied in Educational Data Mining , 2015 .

[12]  Cláudia Antunes,et al.  A structured view on pattern mining-based biclustering , 2015, Pattern Recognit..

[13]  Tutut Herawan,et al.  A Systematic Review on Educational Data Mining , 2017, IEEE Access.

[14]  Rui Henriques,et al.  BicPAM: Pattern-based biclustering for biomedical data analysis , 2014, Algorithms for Molecular Biology.

[15]  Ali Buldu,et al.  Data mining application on students’ data , 2010 .

[16]  Rui Henriques,et al.  BiC2PAM: constraint-guided biclustering for biological data analysis with domain knowledge , 2016, Algorithms for Molecular Biology.

[17]  Rui Henriques,et al.  BSig: evaluating the statistical significance of biclustering solutions , 2017, Data Mining and Knowledge Discovery.