© The Bay Area Learning Analytics Conference. 

SCHEDULE

Schedule

Saturday, March 2, 2019

8:30 -  9.00 Registration and breakfast (Light breakfast provided)

9:00 -  9:15 Opening

9:15 - 10:45 Invited session I

Mitchell Stevens

Director of the Center of Advanced Research through Online Learning (CAROL)
Personalization, Prediction, Tracking: Parsing Responsible Use of Student Data in Higher Education

Alina von Davier

Senior Vice President, ACTNext
An Illustration of an AI-based Educational Assistant and Its Underlying Learning Analytics

Shivani Rao

Senior Applied Researcher, LinkedIn 
An overview of AI problems applied to the domain of Online Learning

 

11:15 - 12:15 Parallel session I

1a: Recommendation and prediction in online environments

 

Yuchi Huang, David Edwards, Lu Ou and Saad Khan (ACTNext)

GMMC: Generating Multimodal Micro Content

Priya Venkat, Sanghamitra Deb and William Ford (Chegg)

Using weak supervision techniques to improve student experiences at Chegg

Shamya Karumbaiah and Ryan S Baker (University of Pennsylvania)

Predicting Quitting in Students Playing a Learning Game

1b: Tutoring 

David Lang, Sigtryggur Kjartansson, Jayadev Bhaskaran and Lucianna Bennoti (Stanford University)

Modeling Student Response Times: Towards Efficient One-on-one Tutoring Dialogues

Katherine Stasaski and Marti Hearst (UC Berkeley) 

Foreign Language Tutoring via Grounded Dialogue

Zoha Zargham, Sakshi Bhargava and Sanghamitra Deb (Chegg)

Personalization at Chegg

 

12:15 - 1:25 Lunch with topic discussions (Light lunch provided)

1:25 - 2:00 Parallel session II

2a: Learning analytics

 

Petr Johanes  (Stanford University) 

Putting the Philosophy of Modeling to Work for Learning Analytics

Ryan Montgomery and Eric Greenwald (UC Berkeley) 

Learning and Analytics, Centered around Evidence ⚡️

Jamie Poskin (TeachFX)

TeachFX: a revolutionary new way to measure student engagement⚡️

2b: MOOCs

Varun Ganapathi, Byung-Hak Kimand Ethan Vizitei (Stanford University/Udacity)

Predicting and Improving Student Performance with Machine Learning

David Lang (Stanford University )

Predicting Clickstream Engagement in MOOCs using Transcript Level Features ⚡️

Yu Su (ACT)

Assessing Self-Learning Outcomes for Complex/Abstract Concepts under Virtual Reality Environment ⚡️

 

2:00 - 2:30 Invited session II

Adam Blum 

Senior Director, Emerging Technologies, ACT

Methods of Intersystem Measurement of Instructional Resource Efficacy

 

2:45 - 3:45 Best practices in efficacy research

Speakers from Digital Promise, Empirical Education, Khan Academy and Rosetta Stone will discuss the intersection of learning analytics and evidence for product efficacy and facilitate a group discussion

4:00 -  5:00 Invited Session III

Zachary Pardos 

Assistant professor of Education and Information, UC Berkeley

Approaches to Scalable Personal Guidance in MOOCs and On Campus 

Emma Brunskill

Assistant professor in Computer Science, Stanford University

AI for Adaptive Curriculum

 

 5:00 -  5:15 Wrap up and networking