Learnersourcing: Improving Video Learning with Large-Scale Learning Interaction Data: Juho Kim, MIT CSAIL (IVC Seminar)

Abstract Millions of learners today use educational videos to master skills and take classes from online platforms such as YouTube, Khan Academy, Coursera, or edX. Massive data from learner activities provides an unprecedented opportunity to enable more interactive and constructive video learning. My research introduceslearnersourcing, a conceptual model in which learners collectively generate useful content for future learners while engaging in a meaningful learning experience themselves. Learnersourcing leads to tools and methods for collecting, processing, and visualizing large-scale learning interaction data. In this talk, I'll present a few example applications of learnersourcing: learners’ second-by-second video interaction data from lecture videos improve video navigation, paid crowd workers extract step-by-step structure from how-to videos, and learners summarize individual steps from how-to videos into higher-level subgoals. With this conceptual framework for incorporating collective learning data into the learning experience, my research attempts to address the technical and motivational challenges in building large-scale, video-based online education platforms. Bio Juho Kim [http://juhokim.com/] is a Ph.D. candidate in the User Interface Design Group at MIT CSAIL (Computer Science and Artificial Intelligence Laboratory). He designs interactive technologies for online education, with a focus on leveraging collective learner activities to enhance the video learning experience. He earned his M.S. in Computer Science from Stanford University in 2010, with a specialization in Human-Computer Interaction, and B.S. in Computer Science and Engineering from Seoul National University, South Korea, in 2008. He also interned at prestigious research labs during his Ph.D., including Microsoft Research, edX, Adobe’s Creative Technologies Lab, and IBM Research. The Samsung Fellowship has supported his graduate studies. Related Papers Data-Driven Interaction Techniques for Improving Navigation of Educational Videos Juho Kim, Philip J. Guo, Carrie J. Cai, Shang-Wen (Daniel) Li, Krzysztof Z. Gajos, Robert C. Miller UIST 2014. Crowdsourcing Step-by-Step Information Extraction to Enhance Existing How-to Videos Juho Kim, Phu Nguyen, Sarah Weir, Philip J. Guo, Robert C. Miller, Krzysztof Z. Gajos CHI 2014. Understanding In-Video Dropouts and Interaction Peaks in Online Lecture Videos Juho Kim, Philip J. Guo, Daniel T. Seaton, Piotr Mitros, Krzysztof Z. Gajos, Robert C. Miller Learning at Scale 2014. Learnersourcing Subgoal Labels for How-to Videos Sarah Weir, Juho Kim, Krzysztof Z. Gajos, Robert C. Miller CSCW 2015. (to appear)