Home   Events   Proceedings   Papers   Resources   Contact  Call for Papers Educational Data Mining Track, Workshop on Data Mining for User Modeling Monday, June 25, 2007 In coordination with the eleventh international conference on User Modeling (http://www.iit.demokritos.gr/um2007/index.php) in Corfu, Greece. PROCEEDINGS NOW AVAILABLE EDUCATIONAL DATA MINING Educational data mining is the process of extracting useful information from educational processes to better understand and assess students and the contexts which they learn in, improve the performance of educational systems, and inform teachers and researchers. Data mining activities include both large scale data analyzed traditionally, as well as more recent advances in machine learning. Educational data mining (EDM) is of particular interest now due to the scaling up of the number of students using interactive learning environments such as intelligent computer tutors. When the field of computer-based education was new, the main challenge of student modeling was to build a basic model of the students' competencies. Few students used such systems, and controlled studies were of brief duration and had relatively few users. In recent years, studies involving computer tutors have scaled up in scope both longitudinally and in the number of users. This increase in scale has created a problem: what to do with the data? For the first time we have the ability to answer educational questions about how individual students will react to instruction, or whether a particular student is not learning material in an expected manner. The missing ingredient is the computational toolkit to organize, visualize, and learn from the data. The aims of this portion of the workshop are: Provide a forum for researchers in computer science, psychometrics, psychology, and education who are investigating educational data mining. Help form collaborations among researchers investigating similar problems but who are perhaps using different approaches. Topics of interest include, but are not limited to: What new types of analyses does data mining enable? Are we now able to attack new problems? How can we integrate computational approaches, prior knowledge, and existing learning theories? How should data mining estimate how users represent the domain? Do subpopulations have different representations? How can data external to learning systems, such as test scores, behavioral observations, and demographic data, be most usefully integrated with usage data? What approaches and features are useful for assessing students? What tools exist that we should be using? What tools don't exist that we should be developing? We are especially interested in papers with a strong evaluation component, particularly those that compare approaches in common use among EDM practitioners. Determining limitations or weaknesses of existing techniques is also on-point. WORKSHOP STRUCTURE The session on Educational Data Mining is a half day and takes place in the context of a broader workshop on Data Mining for User Modeling (http://www.iit.demokritos.gr/um2007/workshops.php). This full-day workshop covers a variety of topics in data mining as it relates to user modeling issues in ubiquitous computing and education, and is composed of three sessions. The morning session is on Educational Data Mining (this webpage) At mid-day there will be a shared session on data mining for UM for education in ubiquitous contexts. This session will consist of an invited talk by Gord McCalla on the 'ecological approach' to e-learning and work on distributed data-centric learner and context modelling in the ARIES lab, and presentations of papers at the intersection of these two areas. The afternoon session will be on Ubiquitous Knowledge Discovery for User Modeling (see http://vasarely.wiwi.hu-berlin.de/K-DUUM07) The workshop aims to bring together researchers and practitioners from a variety of backgrounds. We expect that participants will come from a variety of research areas, including: user modelling, ubiquitous computing, student modeling, personalization, Web mining, machine learning, intelligent tutoring systems, and assessment. We are considering both papers describing original, unpublished research (10 pages max) as well as position papers and work at the formative stage (5 pages max). Submissions should be in LNCS format (see http://www.springer.com/east/home/computer/lncs?SGWID=5-164-7-72376-0). Submissions should be emailed to dm.um07@googlemail.com, and indicate the target session (EDM, K-DUUM, or shared session). All submissions will be reviewed by three (or more) reviewers. All submissions should be emailed by 11:59pm Hawaii time, on February 7, 2007. ORGANIZATION Workshop chairs Ryan S.J.d. Baker -- University of Nottingham Joseph E. Beck -- Carnegie Mellon University Bettina Berendt -- Humboldt University Berlin Alexander Kröner -- German Research Center for Artificial Intelligence Ernestina Menasalvas -- Universidad Politécnica de Madrid Stephan Weibelzahl -- National College of Ireland, Dublin  Program Committee Ricardo Baeza-Yates, Director of Yahoo! Research Barcelona, Spain and Yahoo! Research Latin America at Santiago, Chile Jörg Baus, German Research Center for Artificial Intelligence, Saarland Univ., Germany Shlomo Berkovsky, University of Haifa, Israel Christophe Choquet, University of Maine, France Michel Desmarais, Ecole polytechnique Montreal Marko Grobelnik, Jozef Stefan Institute, Ljubljana, Slovenia Dominik Heckman, German Research Center for Artificial Intelligence, Germany Pilar Herrero, Universidad Politécnica de Madrid, Spain Anthony Jameson, German Research Center for Artificial Intelligence, Germany Judy Kay, University of Sydney Christian Kray, Informatics Research Institute. University of Newcastle, UK Bruce McLaren, DFKI Tanja Mitrovic, University of Canterbury Dunja Mladenic, Jozef Stefan Institute, Ljubljana, Slovenia Bamshad Mobasher, DePaul University Chicago, Chicago / IL, USA Junichiro Mori, University of Tokio, Japan Katharina Morik, University of  Dortmund,  Germany Helen Pain, University of Edinburgh Kaska Porayska-Pomsta, University of London Thorsten Prante, Fraunhofer IPSI, Germany Cristobal Romero, Universidad de Cordoba, Spain Valerie Shute, ETS Sebastian Ventura, Universidad de Cordoba, Spain Silvia Viola, Universita' Politecnica delle Marche, Italy Titus Winters, DirecTV Kalina Yacef, University of Sydney Panayiotis Zaphiris,City University London, UK