Educational Data Mining Workshop
Educational data mining is the process of converting raw data from educational systems to useful information that can be used to inform design decisions and answer research questions. Data mining encompasses a wide range of research techniques that includes more traditional options such as database queries and simple automatic logging as well as more recent developments in machine learning and language technology.
Educational data mining techniques are now being used in ITS and AIED research worldwide. For example, researchers have used educational data mining to:
- Detect affect and disengagement
- Detect attempts to circumvent learning called "gaming the system"
- Guide student learning efforts
- Develop or refine student models
- Measure the effect of individual interventions
- Improved teaching support
- Predict student performance and behavior
However, these techniques could achieve greater use and bring wider benefits to the ITS and AIED communities. We need to develop standard data formats, so that researchers can more easily share data and conduct meta-analysis across tutoring systems, and we need to determine which data mining techniques are most appropriate for the specific features of educational data, and how these techniques can be used on a wide scale. The workshop will provide a forum to present preliminary but promising results that can advance our knowledge of how to appropriately conduct educational data mining and extend the field in new directions.
Aims of the Workshop
- Facilitate the international dissemination of information relating to educational data mining
- Maintain the momentum in this field of study and identify key milestones for the future
- Develop and strengthen a community around this field of study to keep researchers aware of other work, sharing data, and establishing international collaborations
They include, but are not limited to:
- What new discoveries does data mining enable?
- What techniques are especially useful for data mining?
- How can we integrate data mining and existing educational theories?
- How can data mining improve teacher support?
- How can data mining build better student models?
- How can data mining dynamically alter instruction more effectively?
- How can data mining improve systems and interventions evaluations?
- How do these evaluations lead to system and intervention improvements?
- How is data mining fundamentally different from other research methods?
Please submit papers in single-spaced, single-column form, using 10 point Times New Roman as the body text font. Submitted papers should be no longer than 10 pages long, including figures. Shorter submissions are fine. Submissions should be emailed to Cecily Heiner email@example.com in PDF format or DOC format. Papers accepted to appear in the workshop proceedings will need to follow the AIED formatting guidelines for workshop papers, following the IOS template used for the main conference.
Each submission will be reviewed by at least two reviewers who will be asked to give constructive criticism in addition to providing overall ratings. Papers that are not clearly classified as accept or reject will be reviewed by an additional meta-reviewer. The review process will favor papers that describe studies based on data from real students using implemented systems, or which describe new tools and techniques that have led to concrete findings or improvements to new or existing tutoring systems. Papers should describe a research problem, position themselves relative to prior work, define an approach, present relevant results, and ideally present concrete evaluations of the approach’s success. Papers will be reviewed for relevance, clarity, validity, novelty, and potential significance.
- EXTENDED May 4, 2007: Submission deadline for workshop papers
- May 18, 2007: Author notification
- June 8, 2007: Final (camera-ready) version deadline for workshop paper
- July 9 or July 10, 2007: Workshop Day! (All Day)
The workshop is expected to be a full day and consist of three sessions with refereed papers. Each session will conclude with a moderated group discussion. During the workshop, we will also a short session introducing the main themes and best papers from our sister workshops at User Modeling(UM) 2007 and ICALT 2007 and possibly other discussions and presentations.
Cecily Heiner, University of Utah, USA (co-chair)
Neil Heffernan, Worcester Polytechnic Institute, USA (co-chair)
Tiffany Barnes, University of North Carolina at Charlotte, USA (co-chair)
Ivon Arroyo, University of Massachusetts Amherst, USA
Ryan Baker, University of Nottingham, UK
Carole Beal, University of Southern California, USA
Joseph Beck, Carnegie Mellon University, USA
Christophe Choquet, University of Maine, France
Rebecca Crowley, University of Pittsburgh School of Medicine, USA
Janice Gobert, The Concord Consortium, USA
Frank Linton, The Mitre Corporation, USA
Bruce M. McLaren, DFKI, Germany and CMU, USA
Agathe Merceron , AIDA, France
Jack Mostow, Carnegie Mellon University, USA
Kaska Porayska-Pomsta, University of Edinburgh, UK
John Stamper, University of North Carolina at Charlotte, USA
Ron Stevens, UCLA School of Medicine, USA
Kalina Yacef, University of Sydney, Australia