JEDM | Journal of Educational Data Mining 2017-09-21T16:50:31-04:00 Andrew Olney Open Journal Systems <p>The Journal of Educational Data Mining (JEDM;&nbsp;<strong>ISSN 2157-2100</strong>) is an international and interdisciplinary forum of research on computational approaches for analyzing electronic repositories of student data to answer educational questions. It is&nbsp;<strong>completely and permanently free and open-access to both authors and readers</strong>.</p> <div>Educational Data Mining is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings in which they learn.</div> <div>The journal welcomes basic and applied papers describing mature work involving computational approaches of educational data mining. Specifically, it welcomes high-quality original work including but not limited to the following topics:</div> <div> <ul> <li class="show">processes or methodologies followed to analyse educational data,</li> <li class="show">integrating the data mining with pedagogical theories,</li> <li class="show">describing the way findings are used for improving educational software or teacher support,&amp;</li> <li class="show">improving understanding of learners' domain representations, and improving assessment of learners' engagement in the learning tasks.</li> </ul> </div> <div>From time to time, the journal also welcomes survey articles, theoretical articles, and position papers, in as much as these articles build on existing work and advance our understanding of the challenges and opportunities unique to this area of research.</div> <div>&nbsp;</div> <div>&nbsp;</div> <div><strong>Editor</strong>: Andrew Olney, University of Memphis, USA</div> <div>&nbsp;</div> <div><strong>Associate Editors</strong>:</div> <div>Ryan S. Baker, University of Pennsylvania, USA</div> <div>Michel C. Desmarais, Polytechnique Montreal, Canada (editor, 2013-2017)</div> <div>Agathe Merceron, University of Applied Sciences, Germany</div> <div>Mykola Pechenizkiy, Technische Universiteit Eindhoven, Netherlands</div> <div> <div>Kalina Yacef, University of Sydney, Australia (founding editor 2008-2013)</div> <div>&nbsp;</div> </div> <div><strong>Web Editor</strong>: Behzad Beheshti, Polytechnique Montreal, Canada</div> <div>&nbsp;</div> <div>Author guidelines and submission guidelines can be found&nbsp;<a href="/index.php/JEDM/about/submissions#authorGuidelines">here</a>. All other inquiries should be emailed to:&nbsp;<a href=""></a>.</div> <div>&nbsp;</div> Editorial Acknowledgements and Introduction to the Special Issue on EDM Journal Track 2017-09-21T16:50:30-04:00 Agathe Merceron Andrew Olney Radek Pelánek <p>The EDM Conference was held in Wuhan this year, from June 25 to June 28, and for the third time it held a Journal track which was edited by Agathe Merceron and Radek Pelánek this year. The Journal track allows papers submitted to JEDM to be presented at the conference. A summary is available in the proceedings, and the full text is published in the Journal.</p> 2017-09-19T15:59:38-04:00 Copyright (c) 2017 Agathe Merceron, Andrew Olney, Radek Pelanek Modeling Student Behavior With Two-Layer Hidden Markov Models 2017-09-21T16:50:31-04:00 Chase Geigle ChengXiang Zhai Massive open online courses (MOOCs) provide educators with an abundance of data describing how students interact with the platform, but this data is highly underutilized today. This is in part due to the lack of sophisticated tools to provide interpretable and actionable summaries of huge amounts of MOOC activity present in log data. To address this problem, we propose a student behavior representation method alongside a method for automatically discovering those student behavior patterns by leveraging the click log data that can be obtained from the MOOC platform itself. Specifically, we propose the use of a two-layer hidden Markov model (2L-HMM) to extract our desired behavior representation, and show that patterns extracted by such a 2L-HMM are interpretable, meaningful, and unique. We demonstrate that features extracted from a trained 2L-HMM can be shown to correlate with educational outcomes. 2017-09-19T15:36:44-04:00 Copyright (c) 2017 JEDM - Journal of Educational Data Mining Closing the loop: Automated data-driven cognitive model discoveries lead to improved instruction and learning gains 2017-09-21T16:50:31-04:00 Ran Liu Kenneth R Koedinger <p class="Abstract">As the use of educational technology becomes more ubiquitous, an enormous amount of learning process data is being produced. Educational data mining seeks to analyze and model these data, with the ultimate goal of improving learning outcomes. The most firmly grounded and rigorous evaluation of an educational data mining discovery is whether it yields better student learning when applied. Such an evaluation has been referred to as "closing the loop", as it completes cycle of system design, deployment, data analysis, and discovery leading back to design. Here, we present an instance of “closing the loop” on an automated cognitive modeling improvement discovered by Learning Factors Analysis (Cen, Koedinger, &amp; Junker, 2006). We discuss our findings from a process in which we interpret the automated improvements yielded by the best-fitting cognitive model, validate the interpretation on novel data, use it to make changes to classroom-deployed educational technology, and show that the changes lead to significant learning gains relative to a control condition.</p> 2017-09-19T15:36:22-04:00 Copyright (c) 2017 JEDM - Journal of Educational Data Mining RiPLE: Recommendation in Peer-Learning Environments Based on Knowledge Gaps and Interests 2017-09-21T16:50:31-04:00 Hassan Khosravi Kendra Cooper Kirsty Kitto Various forms of Peer-Learning Environments are increasingly being used in postsecondary education, often to help build repositories of student generated learning objects. However, large classes can result in an extensive repository, which can make it more challenging for students to search for suitable objects that both reflect their interests and address their knowledge gaps. Recommender Systems for Technology Enhanced Learning (RecSysTEL) offer a potential solution to this problem by providing sophisticated filtering techniques to help students to find the resources that they need in a timely manner. Here, a new RecSysTEL for Recommendation in Peer-Learning Environments (RiPLE) is presented. The approach uses a collaborative filtering algorithm based upon matrix factorization to create personalized recommendations for individual students that address their interests and their current knowledge gaps. The approach is validated using both synthetic and real data sets. The results are promising, indicating RiPLE is able to provide sensible personalized recommendations for both regular and cold-start users under reasonable assumptions about parameters and user behavior. 2017-05-24T07:19:34-04:00 Copyright (c) 2017 JEDM - Journal of Educational Data Mining