Following up on the success of the 2010 KDD Cup competition, this workshop seeks to engage the cutting edge data mining community with the education community. We solicit papers addressing problems such as predicting future student performance and learning the underlying structure of student knowledge from large educational datasets. The 2010 KDD Cup competition showed that many traditional data mining techniques could be successfully applied to educational data to improve prediction. This workshop will be a venue to continue this research and further explore the nature of educational data and what factors are important in determining student knowledge.
The first objective of this workshop is to explore the opportunities for knowledge discovery in educational data. Educational data is becoming increasingly rich as more and more educational systems are going online and collecting large amounts of data. Repositories such as the Pittsburgh Science of Learning Center DataShop (http://pslcdatashop.web.cmu.edu) contain a large number of available data sets that present tremendous research opportunities for the larger SIGKDD. These datasets are primarily from tutors focused on STEM (Science, Technology, Engineering and Mathematics) topics such as Algebra, Geometry, Physics, Chemistry and others.
The second objective is to provide a bridge to connect the relatively new educational data mining community to the SIGKDD community. As seen in the 2010 KDD Cup competition, there are a number of interesting educational data mining problems that could benefit from the methods discussed and presented at SIGKDD.
| Time | Duration | |
| Welcome and Introduction | 1:00pm | 15 min |
| A Learning Design Recommendation System Based on Markov Decision Processes Guillaume Durand, Francois LaPlante, and Rita Kop (pdf) |
1:15pm | 15 min |
| Anticipating Teachers' Performance Joana Barracosa and Claudia Antunes (pdf) |
1:30pm | 15 min |
| Improving Pedagogy by Analyzing Relevance and Dependency of Course Learning Outcomes Thomas Devine, Mahmood Hossain, Erica Harvey, and Andreas Baur (pdf) |
1:45pm | 15 min |
| The Sum is Greater than the Parts: Ensembling Student Knowledge Models in ASSISTments Sujith Gowda, Ryan S.J.D. Baker, Zachary Pardos and Neil Heffernan (pdf) |
2:00pm | 20 min |
| Multi-relational Matrix Factorization Models for Predicting Student Performance Nguyen Thai-Nghe, Lucas Drumond, Tomas Horvath and Lars Schmidt-Thieme (pdf) |
2:20pm | 20 min |
| Response Tabling - A simple and practical complement to Knowledge Tracing Qing Yang Wang, Paul Kehrer, Zachary Pardos and Neil Heffernan (pdf) |
2:40pm | 20 min |
| Break | 3:00pm | 15 min |
| Towards Identifying Teacher Topic Interests and Expertise within an Online Social Networking Site Sen Cai, Siddharth Jain, Yu-Han Chang and Jihie Kim (pdf) |
3:15pm | 15 min |
| An Analysis of Response Time Data for Improving Student Performance Prediction Xiaolu Xiong, Zachary Pardos and Neil Heffernan (pdf) |
3:30pm | 15 min |
| From Data to Actionable Knowledge: A Collaborative Effort with Educators Sharath Srinivas, Eric Hamby, Robert Lofthus, Edward Caruthers, Jan Barett and Erin Ells (pdf) |
3:45pm | 15 min |
| Analyzing the language evolution of a science classroom via a topic model Mohammad Khoshneshin, Mohammad Ahmadi Basir, Padmini Srinivasan, Nick Street and Brian Hand (pdf) |
4:00pm | 20 min |
| Using Graphical Models to classify Dialogue Transition in Online Q&A Discussion Soo Won Seo, Jeon-Hyung Kang, Joanna Drummond and Jihie Kim (pdf) |
4:20pm | 20 min |
| Comparative Action Sequence Analysis with Hidden Markov Models and Sequence Mining John Kinnebrew and Gautam Biswas (pdf) |
4:40pm | 20 min |
| Towards Automatic Hint Generation for a Data-Driven Novice Programming Tutor Wei Jin, Lorrie Lehmann, Matthew Johnson, Michael Eagle, Behrooz Mostafavi, Tiffany Barnes and John Stamper (pdf) |
5:00pm | 15 min |
| Closing |
5:15pm | 15 min |
We welcome papers describing original work. Areas of interest include but are not limited to:
The following large educational datasets have been made available for easy download:
There are two types of submission:
All submissions should follow the ACM single column formatting guidelines (MS Word, LaTeX).
Submission is managed by EasyChair. You’ll need to register (free and quick procedure). To enter the conference submission section, please go to: http://www.easychair.org/conferences/?conf=kddined2011.
Authors of accepted papers will be invited to submit extended versions of papers to an upcoming special issue of the Journal of Educational Data Mining on the KDD 2011 Knowledge Discovery in Educational Data workshop.
| Workshop Committee | |
| John Stamper | Carnegie Mellon University |
| Kenneth R. Koedinger | Carnegie Mellon University |
| Geoff Gordon | Carnegie Mellon University |
| Ryan Baker | Worcester Polytechnic Institute |
| Alexandru Niculescu-Mizil | NEC Laboratories America |
| Chih-Jen Lin | National Taiwan University |
| Philip Pavlik | Carnegie Mellon University |
| Ted Carmichael | University of North Carolina at Charlotte |
| Neil Heffernan | Worcester Polytechnic Institute |
| Zach Pardos | Worcester Polytechnic Institute |
| Steve Ritter | Carnegie Learning, Inc. |
| Luo Si | Purdue University |
| Guatam Biswas | Vanderbilt University |
Contact John Stamper—john AT stamper DOT org