Graph-based Educational Data Mining

Collin F. Lynch, Tiffany Barnes, Linting Xue, Niki Gitinabard
2017 Educational Data Mining  
With the growing popularity of MOOCs and computer-aided learning systems, as well as the growth of social networks in education, we have begun to collect increasingly large amounts of educational graph data. This graph data includes complex user-system interaction logs, student-produced graphical representations, and conceptual hierarchies that large amounts of graph data have. There is abundant pedagogical information beneath these graph datasets. As a result, graph data mining techniques such
more » ... as graph grammar induction, path analysis, and prerequisite relationship prediction has become increasingly important. Also, graphical model techniques (e.g. Hidden Markov Models or probabilistic graphical models) has become more and more important to analyze educational data. While educational graph data and data analysis based on graphical models has grown increasingly common, it's necessary to build a strong community for educational graph researchers. This workshop will provide such a forum for interested researchers to discuss ongoing work, share common graph mining problems, and identify technique challenges. Researchers are encouraged to discuss prior analyses of graph data and educational data analyses based on graphical models. We also welcome discussions of in-progress work from researchers seeking to identify suitable sources of data or appropriate analytical tools.
dblp:conf/edm/LynchBXG17 fatcat:rdgcxjcklbcrpnlrce42xyemmy