KAIST - COMPUTER SCIENCE

  • korea
  • search
  • login

Directions

navi

[HCI＠KAIST Seminar] Prof. Joseph Jay Williams, NUS

Mon, Jul 31, 2017 @ 16:30~17:30
Prof. Joseph Jay Williams
Seminar

HCI＠KAIST is organizing a seminar with Prof. Joseph Jay Williams from the National University of Singapore's School of Computing. He works at the intersection of online education, cognitive science, HCI, and machine learning, with a specific focus on large-scale experimentation. His research has introduced many interesting experimental models that attempt at achieving lab-level rigor and web-level scale at the same time.
  • When: 4:30-5:30pm on July 31 (Next Monday)
  • Where: Room 102, Building N1
  • Title: Perpetually enhancing human learning through dynamic, personalized, collaborative experimentation
    • Additionally, if you would like to have a 1-on-1 meeting with Prof. Williams, please sign up by using the link below. He is available from July 31 to August 2. Both students and faculty are welcome to sign up.
    --
    Title
    Perpetually enhancing human learning through dynamic, personalized, collaborative experimentation
    Abstract
    There is a proliferation of websites and mobile apps for helping people learn new concepts (e.g. online courses), and learn how to change health habits and behavior (e.g. websites for reducing depression, apps for quitting smoking). How can we use data from real-world users to rapidly enhance and personalize these technologies? I show how we can build self-improving systems through three applications of MOOClets/AdapComps, a conceptual framework implemented in technology that leverages randomized A/B experiments as tools for collaboration, dynamic enhancement, and adaptive personalization.
    First, a novel system that enhanced learning from K12 math problems, by crowdsourcing explanations and using machine learning to automatically experiment to discover the best explanations. Second, a system which enabled three on-campus instructors at Harvard to experimentally investigate which hints and feedback messages students found helpful, enabling more ethical experimentation by dynamically presenting the best conditions to future students. Third, I show how to boost responses to an email campaign in a MOOC, by experimentally discovering how to personalize motivational messages to a user's activity level.
    These self-improving systems use experiments as a bridge between designers, social-behavioral scientists and researchers in statistical machine learning. I'll present future directions, such as investigating which reflection prompts help students learn, how to enhance motivation through social-psychological interventions, and how to personalize web-apps that help students set and achieve micro-goals. I will also discuss efforts to bridge education with health behavior change and marketing.
    Bio
    Joseph Jay Williams is an Assistant Professor at the National University of Singapore's School of Computing, in the department of Information Systems & Analytics. He was previously a Research Fellow at Harvard's Office of the Vice Provost for Advances in Learning, and a member of the Intelligent Interactive Systems Group in Computer Science. He completed a postdoc at Stanford University in the Graduate School of Education in Summer 2014, working with the Office of the Vice Provost for Online Learning and the Open Learning Initiative. He received his PhD from UC Berkeley in Computational Cognitive Science, where he applied Bayesian statistics and machine learning to model how people learn and reason. He received his B.Sc. from University of Toronto in Cognitive Science, Artificial Intelligence and Mathematics, and is originally from Trinidad and Tobago. More information about his research and papers is at www.josephjaywilliams.com.

    Location: Room 102, Building N1
    Posted By: Administrator

    list