Educational Data Mining Intelligent Tutoring Systems The Learning Sciences Gaming the System
Ryan S. Baker                                                                                                


I am tenured Associate Professor in the Graduate School of Education at the University of Pennsylvania. My primary appointment is in the Teaching, Learning, and Leadership Division. I am also affiliated with the Higher Education Division and anticipate a future courtesy affiliation with Computer and Information Science in the School of Engineering and Applied Science (pending).

I direct the Penn Center for Learning Analytics, which is so awesomely new that it doesn't have a webpage yet.

I also have an affiliate appointment at Worcester Polytechnic Institute, in the Department of Social Science and Policy Studies, and have courtesy appointments in the Department of Human Development at Teachers College Columbia University and at the University of Edinburgh Moray House School of Education

I am Associate Editor of the Journal of Educational Data Mining and the International Journal of Artificial Intelligence and Education.

I am co-Lead of the Big Data in Education Spoke of the NSF Northeast Big Data Innovation Hub.

I will be Program Chair of the Artificial Intelligence in Education Conference in 2017.

      "Data, glorious data"

I taught the MOOC Big Data and Education on EdX; it will re-launch in Fall 2016 (anticipated).
In the meantime, please see my MOOT (Massive Online Open Textbook), Big Data and Education, based on the MOOC.

My research is at the intersection of Educational Data Mining and Human-Computer Interaction. I develop and use methods for mining the data that comes out of the interactions between students and educational software, in order to better understand how students respond to educational software, and how these responses impact their learning. I study these issues within intelligent tutors and educational games.

In recent years, my colleagues and I have developed automated detectors that make inferences in real-time about students' affect and motivational and meta-cognitive behavior, using data from students' actions within educational software (no sensor, video, or audio data). We have in particular studied gaming the system, off-task behavior, carelessness, "WTF behavior", boredom, frustration, engaged concentration, and appropriate use of help and feedback. We use these models to make basic discoveries about human learning and learners. Many of these models are developed using data collected through the Baker Rodrigo Ocumpaugh Monitoring Protocol (BROMP), and the HART Android app.

I have made some tools for EDM research available here.

My daughter and I created a card game, Academic Squabble

Selected Current and Upcoming Projects

  • Predicting STEM Career Choice from Computational Indicators of Student Engagement within Middle School Mathematics Classes (funded by NSF ITEST)
  • Classroom Environment, Allocation of Attention, and Learning Outcomes in K-4 Students (funded by IES)
  • Detectors of Affect in Educational Software (funded by NSF and Gates Foundation)
  • Detecting, Studying, and Adapting to Affect in Military Training (cooperative agreement with Army Research Laboratory)
  • Creating Design Patterns for More Engaging Educational Software, Based on Evidence from EDM (funded by NSF REAL)
  • Studying Social Factors that Impact Community Participation After Use of MOOCs (funded by NSF DIRITL)
  • Studying Participation in Online Courses By Students From Underrepresented Groups (funded by Gates Foundation)
  • Student Behavior in Educational Software Across Cultures

Please check out my publications web page for recent papers.

Follow my research group on Twitter or Facebook.

Quantitative Field Observation Affective Computing Human-Computer Interaction Psychometric Machine-Learned Models