Ateneo Laboratory for the Learning Sciences

The 10th International Conference on Computers on Educational Data Mining and the 18th International Conference on Artificial Intelligence in Education were held last June 25 to 28 and June 29 to July 1 in Wuhan, China. In attendance were six members of the Ateneo Laboratory for the Learning Sciences: Dr. Ma. Mercedes Rodrigo, May Marie P. Talandron, Cristina E. Dumdumaya, Maureen Mamilic-Villamor, Cristina Enriquez and Yancy Paredes.

The following conference papers and poster papers were accepted into the conference and presented that week:1. Characterizing Collaboration in the Pair Program Tracing and Debugging

1. Characterizing Collaboration in the Pair Program Tracing and Debugging
   Eye-Tracking Experiment by Maureen Villamor and Dr. Rodrigo — short paper,
   EDM
2. Assessing the Collaboration Quality in the Pair Program Tracing and
   Debugging Eye-Tracking Experiment by Maureen Villamor, Yancy Vance Paredes, Japeth Duane Samaco, Joanna Feliz Cortez, Joshua Martinez, and Ma. Mercedes Rodrigo – poster, AIED
3. Modeling the Incubation Effect among Students Playing an Educational Game
   for Physics by May Marie P. Talandron, Ma. Mercedes Rodrigo, and Joseph Beck
   – full paper, AIED
4. Regional Cultural Differences in How Students Customize Their Avatars in
   Technology-Enhanced Learning by Cristina E. Dumadaya, Evelyn Yarzebinski,
   Ma. Mercedes T. Rodrigo, Noboru Matsuda, and Amy Ogan – poster, AIED
5. Proficiency and Preference Using Local Language with a Teachable Agent
   by Cristina E. Dumadaya, Amy Ogan, Evelyn Yarzebinski, Roberto De Roock, Ma.
   Mercedes Rodrigo, and Michelle Banawan – poster, AIED
6. Constraint-Based Modelling as a Tutoring Framework for Japanese Honorifics by Zachary Chung, Takehito Utsuro, and Ma. Mercedes Rodrigo – poster, AIED

Monday, 10 July 2017, 9:00 to 4:00
Ateneo de Manila University (Exact room TBA)
ADMISSION IS FREE

Deep Learning with Educational Data
Joseph Beck, Ph.D.

This whole-day lecture focuses on applications of deep learning for educational data. Deep learning is a machine learning approach using neural networks with multiple levels of representational transformation (i.e., hidden layers). Deep learning has been used in a variety of domains over the past five years with impressive results. Recently, it has been used for educational data sets with mixed results when compared to traditional modeling methodologies.

In this lecture, Dr. Beck will provide an introduction to machine learning followed quickly by a discussion of deep learning. He will discuss applications as well as current work.

Joseph Beck, assistant professor of Computer Science, has been at Worcester Polytechnic Institute since 2007. His research focuses on educational data mining, a new discipline that develops techniques for analyzing large educational data sets to make discoveries that will improve teaching and learning. His work centers on estimating how computer tutors impact learning. He established the first workshop in the field and in 2008 was program co-chair of the first International Conference on Educational Data Mining. He holds a BS in mathematics, computer science, and cognitive science from Carnegie Mellon University, and a PhD in computer science from the University of Massachusetts, Amherst.

To register, please sign up here.

Dr. Gloria Washington is an Assistant Professor at Howard University in the Computer Science Department. At Howard, she runs the Affective Biometrics Lab and performs research with her students on affective computing, biometrics, and computer science education. Her research is supported by the Department of Homeland Security, Leidos, and the TIDES Foundation. Before coming to Howard University she was an Intelligence Community Postdoctoral Research Fellow in the Department of Computing Science at Clemson University. She performed research on identifying individuals based solely from pictures of their ears. Dr. Washington has more than fifteen years in Government service and has presented on her research throughout industry. Ms. Washington holds M.S. and Ph.D. in Computer Science from The George Washington University, and a B.S. in Computer Information Systems from Lincoln University of Missouri.

Dr. Washington’s talk had highlighted that the incidence of children with chronic disease is growing in the U.S. and these children have special educational needs that relate to the way they learn how to care for themselves. Children with chronic disease learn positive health behaviors taught through self-management education taught by patient advocates, nurses, and their families. Unfortunately, this education usually begins around age 10 or 12; leading some to develop unhealthy habits and lack self-efficacy in improving their health. Fitness trackers were first created to help adults keep abreast of their fitness goals. However, these devices are slowly being introduced to children. There are no health and wellness technologies that are designed for children and exploit human physiological information to interpret and empathize with a child’s mental and/or physical health. Additionally, social cognitive models/theories were developed to help educational professionals identify the factors that influence how a person learns positive and negative health behaviors. These models include factors related to ethnicity, age, and socioeconomic status. Although these factors have proved significant in helping to design educational interventions for health psychologists; these theories have not been adapted for creation of educational materials relevant to children with chronic disease. There exists an opportunity for a new genre of fitness trackers that empathizes with the user, teaches positive health behaviors, contributes to a child’s self-efficacy and emphasizes the scientific underpinnings of a disease. This tool should also allow children the ability to teach themselves, their peers, and their caregivers through show and tell, positive reinforcement, and fun game-based activities. This talk focuses on introduction of a new empathetic fitness tracker that is used for instructional teaching of young children with chronic disease.