Concept Graph Learning from Educational Data

Abstract

This paper addresses an open challenge in educational data mining, i.e., the problem of using observed prerequisite relations among courses to learn a directed universal concept graph, and using the induced graph to predict unobserved prerequisite relations among a broader range of courses. This is particularly useful to induce prerequisite relations among courses from different providers (universities, MOOCs, etc.). We propose a new framework for inference within and across two graphs-at the course level and at the induced concept level-which we call Concept Graph Learning (CGL). In the training phase, our system projects the course-level links onto the concept space to induce directed concept links; in the testing phase, the concept links are used to predict (unobserved) prerequisite links for test-set courses within the same institution or across institutions. The dual mappings enable our system to perform an interlingua-style transfer learning, e.g. treating the concept graph as the interlingua, and inducing prerequisite links in a transferable manner across different universities. Experiments on our newly collected data sets of courses from MIT, Caltech, Princeton and CMU show promising results, including the viability of CGL for transfer learning.

Concept Extraction and Prerequisite Relation Learning from Educational Data

“…A few efforts aim to learn prerequisite relations from educational data, such as courses (Yang et al 2015;Liang et al 2015;Liu et al 2016;Liang et al 2017), MOOCs (Pan et al 2017a), textbooks Liang et al 2018) and scientific papers (Gordon et al 2016).…”

“…However, recent researches mainly focus on keyword extraction (Mihalcea and Tarau 2004;Liu, Chen, and Sun 2011;Tixier, Malliaros, and Vazirgiannis 2016) or highquality phrase mining (Liu et al 2015;Shang et al 2018), and there are only a few efforts aiming to extract domainspecific concepts and learn prerequisite relations from educational data, such as courses (Yang et al 2015;Liang et al 2015;Liu et al 2016;Liang et al 2017), MOOCs (Massive Open Online Courses) (Pan et al 2017a), textbooks Liang et al 2018) and scientific papers (Gordon et al 2016).…”

Prerequisite-related MOOC recommendation on learning path locating

“…In most research, prerequisite correlation is mainly calculated through knowledgebased concepts analysis. Yang built the concept map through the prerequisite relationship of the existing curriculums and used the concept map to predict the prerequisite [5]. Liu studies the learning dependence between knowledge points through text analysis [6].…”

Design Assistant for NoSQL Technology Selection

“…We are currently investigating the use of machine learning to automate the feature model population of QuABaseBD, using the Concept Graph Learning (CGL) machine learning method [14].…”