Education remains an outdated process that requires extensive human effort from course instructors and students: instructors need to prepare teaching materials, manually grade students’ homework, and provide feedback to the students on their learning progress. Students, on the other hand, typically go through an extremely burdensome “one-size-fits-all” learning process that is not personalized to their abilities, needs, and learning context. Building on a rich history of AI, psychology, and education, recent advances in machine learning provide new opportunities to tackle the above challenges by collecting and analyzing the data students generate when they interact with a learning system. Areas of recent progress include:

• Learning analytics that build statistical models of student knowledge to provide computerized and personalized feedback on learning the students’ progress and their instructors
• Content analytics that organize and optimize content items like assessments, textbook sections, lecture videos, etc.
• Scheduling algorithms that search for an optimal and adapted teaching policy that helps students learn more efficiently
• Grading systems that assess and score student responses to assessments and computer assignments at large scale, either automatically or via peer grading
• Cognitive psychology, where data mining is becoming a powerful tool to validate the theories developed in cognitive science and facilitate the development of new theories to improve the learning process and knowledge retention
• Active learning and experimental design, which adaptively select assessments and other learning resources for each student individually to enhance learning efficiency

The goal of this workshop is to bring together experts from different fields of machine learning, cognitive science, and education to explore the interdisciplinary nature of research on this topic. In particular, we aim to elicit new connections among these diverse fields, identify novel tools and models that can be transferred from one to the others, and explore novel machine learning applications that will benefit the education community. We believe that a successful workshop will lead to new research directions in a variety of areas and will also inspire the development of novel theories and tools.

For more information about the ICML conference, please visit http://icml.cc/2015/.

ORGANIZERS

• Richard G. Baraniuk, Rice University
• Emma Brunskill, Carnegie Mellon University
• Jonathan Huang, Google
• Mihaela van der Schaar, University of California Los Angeles
• Michael C. Mozer, University of Colorado Boulder
• Christoph Studer, Cornell University
• Andrew S. Lan, Rice University

CALL FOR PAPERS

We invite the submission of papers on all topics related to the application of machine-learning theory and/or algorithms to education, including but not limited to:

• Learning analytics and student modeling
• Content analytics and text mining
• Teaching policy optimization and personalization
• Automatic and peer grading
• The cognitive science of learning
• Active learning and experimental design
• Data analysis for emerging educational platforms (MOOCs, educational games, etc.)

Submissions should follow the regular ICML paper format; there is no page limit. Papers submitted for review do not need to be anonymized. Accepted papers will be made available on the workshop website, since there will be no official proceedings. Accepted papers will be presented either as a talk or as a poster. We welcome submissions with either results that have not been published previously or a summary of the authors’ previous work that has been recently published or is under review in another conference or journal. In the interest of spurring the discussion, we also encourage authors to submit extended abstracts and work-in-progress papers with only preliminary results.

PAPER SUBMISSION

Submissions will be judged on their novelty and potential impact in the emerging field of machine learning for education.

Please send your submissions via email to ml4ed.icml15@gmail.com

Questions about the workshop can be sent to the same e-mail address.

IMPORTANT DATES

• Paper submission deadline: May 1, 2015
• Author notification: May 10, 2015
• Camera ready versions of accepted submissions: May 22, 2015
• Final workshop schedule: May 25, 2015
• Workshop: July 10, 2015

SCHEDULE

8:30–8:35 Opening remarks – Workshop organizers

Session 1

8:35–9:00 Talk 1: Mihaela van der Schaar, UCLA One Teacher for Every Student: Personalizing Education

9:00–9:25 Talk 2: Andrew Lan, Rice University Modeling Student Responses Using the Dealbreaker Model

9:25–9:50 Talk 3: Siddharth Reddy, Cornell University Learning Representations of Student Knowledge and Educational Content

9:50–10:10 Talk 4: Mehdi Sajjadi, University of Hamburg Peer Grading in a Course on Algorithms and Data Structures: Machine Learning Algorithms do not Improve over Simple Baselines

10:10–10:30 Coffee Break

Session 2

10:30–10:55 Invited talk 5: Mykola Pechenizkiy, Eindhoven University of Technology Grand challenges in Educational Data Mining

10:55–11:20 Invited talk 6: Jerry Zhu, University of Wisconsin Madison Machine Teaching

11:20–11:45 Invited talk 7: Piyush Rai, Duke University Scalable Bayesian Latent Factor Models for Binary Matrices and Tensors

11:45–12:10 Invited talk 8: Zoran Popovic, University of Washington Generative Optimization of the Learning Ecosystem

12:10–12:15 Poster Spotlight

12:10–14:00 Lunch Break

Session P: Poster Session

14:00–14:30 Poster Session

Session 3

14:30–14:55 Invited talk 9: Mehran Sahami, Stanford University Statistical Modeling to Understand the Dynamics of Student Populations

14:55–15:20 Invited talk 10: Igor Labutov, Cornell University

Curriculum Mining: Towards Connecting Resources that Explain 15:20–15:45 Invited talk 11: Burr Settles, Duolingo

Machine Learning for Spaced Repetition and Variable Rewards 15:45–16:10 Invited talk 12: Jacob Whitehill, HarvardX

Automatic Recognition of Student (Dis)engagement

16:10–16:30 Coffee Break

Session 4

16:30–16:55 Invited talk 13: Alina von Davier, ETS Virtual & Collaborative Assessments: Examples, Implications and Challenges for Educational Measurement

16:55–17:20 Invited talk 14: Joseph Jay Williams, HarvardX MOOClets: An Abstraction and API for Machine Learning Research to Optimize and Personalize Users’ Interactions with Large-scale Online Technologies

17:20–17:45 Invited talk 15: Chris Piech, Stanford University Deep Knowledge Tracing

17:45–18:00 General discussion and closing remarks

POSTERS

What do We Know about MOOC Students Caring More about Content than Platform? - One Step toward Defining MOOC Learner Success Yuan Wang, Columbia University

T-SKIRT: Online Estimation of Student Proficiency in an Adaptive Learning System Chaitu Ekanadham, Yan Karklin, Knewton

Learning Representations of Student Knowledge and Educational Content Siddharth Reddy, Igor Labutov, Thorsten Joachims, Cornell University

Learning Models for Personalized Educational Feedback and Job Selection Vinay Shashidhar, Shashank Srikant, Varun Aggarwal, Aspiring Minds

The Leopard Framework: Towards Understanding Educational Technology Interventions with a Pareto Efficiency Perspective Jose Gonzalez-Brenes, Pearson, Yun Huang, University of Pittsburgh

Tensor Factorization for Student Modeling and Performance Prediction in Unstructured Domain Shaghayegh Sahebi, Yu-Ru Lin, Peter Brusilovsky, University of Pittsburgh

Scaling cognitive modeling to massive open environments Yanbo Xu, Matthew Johnson, Zachary Pardos, University of California Berkeley