Keynotes
Opening keynote:
Zoran Popovic
Professor and Director the Center for Game Science, University of Washington
Founder and Chief Scientist, Enlearn
Closing keynote, open to CSCW attendees:
Director of Research, Google Inc.
Machine Learning for Learning at Scale
There is great enthusiasm for the idea that massive amounts of data from online interactions of learners with material can lead to a rapid improvement cycle, driven by analysis of the data, experimentation, and intervention to do more of what works and less of what doesn't. This talk discusses techniques for working with massive amounts of data.
Preliminary Program
Session 1: Analysis
Incremental training of models for large-scale implementation of automated writing evaluation. Nicholas Dronen (University of Colorado at Boulder & Pearson), Peter Foltz (Pearson & University of Colorado at Boulder), and Kyle Habermehl (Pearson)
Improving Student Modeling Through Partial Credit and Problem Difficulty. Korinn Ostrow, Christopher Donnelly, Seth Adjei, and Neil Heffernan (Worcester Polytechnic Institute)
Addressing Common Analytic Challenges to Randomized Experiments in MOOCs: Attrition and Zero-Inflation. Anne Lamb, Jascha Smilack, Andrew Ho, and Justin Reich (Harvard University)
Structure and messaging techniques for online peer learning systems that increase stickiness. Yasmine Kotturi (UC San Diego), Chinmay Kulkarni and Michael Bernstein (Stanford), and Scott Klemmer (UC San Diego)
Session 2: Behavior 1
The Prediction of Student First Response Using Prerequisite Skills. Anthony Botelho, Hao Wan, and Neil Heffernan (Worcester Polytechnic Institute)
Blended learning in Indian colleges with Massively Empowered Classroom. Edward Cutrell, Jacki O'Neill, Nitish Bhanuprakash, Andrew Cross, Nakull Gupta, and Srinath Bala (Microsoft Research), Viraj Kumar (PES University), and William Thies (Microsoft Research)
Attrition in Massive Open Online Courses: Inequalities, Dropout Reasons, and Psychological Factors. René F. Kizilcec and Sherif Halawa (Stanford University)
Towards Detecting Wheel-Spinning: Future Failure in Mastery Learning. Yue Gong and Joseph E. Beck (Worcester Polytechnic Institute)
Session 3: Behavior 2
Rapid peer feedback in MOOCs emphasizes iteration and improves performance. Chinmay Kulkarni and Michael S Bernstein (Stanford University) and Scott R Klemmer (UC San Diego)
Alumni & Tenured Participants in MOOCs: Analysis of Two Years of MOOC Discussion Channel Activity. Matti Nelimarkka (Helsinki Institute for Information Technology HIIT, Aalto University & Dep. CS, University of Helsinki) and Arto Vihavainen (University of Helsinki)
A Playful Game Changer: Fostering Student Retention in Online Education with Social Game Elements. Markus Krause, Marc Mogale, and Henning Pohl (Leibniz University Hannover) and Joseph Williams (Stanford University/Harvard University)
moocRP: an open-source analytics platform. Zachary Pardos and Kevin Kao (UC Berkeley)
Session 4: Learning
Learning is Not a Spectator Sport: Doing is Better than Watching for Learning from a MOOC. Kenneth R. Koedinger, Jihee Kim, Julianna Zhuxin Jia, Elizabeth A. McLaughlin, and Norman L. Bier (Carnegie Mellon University)
Exploring the Effect of Confusion in Discussion Forums of Massive Open Online Courses. Diyi Yang, Miaomiao Wen, Iris Howley, Robert Kraut, and Carolyn Rose (Carnegie Mellon University)
Uncovering Trajectories of Informal Learning in Large Online Communities Of Creators. Seungwon Yang, Carlotta Domeniconi, Matt Revelle, Mack Sweeney, Ben U. Gelman, Chris Beckley, and Aditya Johri (George Mason University)
Probabilistic Use Cases: Discovering Behavioral Patterns for Predicting Certification. Cody A. Coleman, Daniel T. Seaton, and Isaac Chuang (MIT)
Session 5: Grading
Bayesian Ordinal Peer Grading. Karthik Raman and Thorsten Joachims (Cornell University)
An Automated Grading/Feedback System for Multiview Engineering Drawings using RANSAC. Youngwook Paul Kwon and Sara McMains (UC Berkeley)
Mathematical Language Processing: Automatic Grading and Feedback for Open Response Mathematical Questions. Andrew Lan, Divyanshu Vats, Andrew Waters, and Richard Baraniuk (Rice University)
BayesRank: A Bayesian Approach to Ranked Peer Grading. Andrew Waters (Rice University), David Tinapple (Arizona State University), and Richard Baraniuk (Rice University)
Session 6: Design
Staggered Versus All-At-Once Content Release in Massive Open Online Courses: Evaluating a Natural Experiment. Tommy Mullaney and Justin Reich
Autonomously Generating Hints by Inferring Problem Solving Policies. Chris Piech, Mehran Sahami, Jon Huang, and Leo Guibas (Stanford)
Problems Before Solutions: Automated Problem Clarification at Scale. Soumya Basu, Albert Wu, Brian Hou, and John DeNero (University of California, Berkeley)