Leveraging Video Interaction Data and Content Analysis to Improve Video Learning

DSpace/Manakin Repository

Leveraging Video Interaction Data and Content Analysis to Improve Video Learning

Citable link to this page

 

 
Title: Leveraging Video Interaction Data and Content Analysis to Improve Video Learning
Author: Kim, Juho; Li, Shang-Wen; Cai, Carrie J.; Gajos, Krzysztof Z; Miller, Robert C.

Note: Order does not necessarily reflect citation order of authors.

Citation: Gajos, Krzysztof Z., Juho Kim, Shang-Wen (Daniel) Li, Carrie J. Cai, and Robert C. Miller. 2014. Leveraging video interaction data and content analysis to improve video learning. In Proceedings of the CHI 2014 Learning Innovation at Scale workshop, Toronto, Canada, April 27, 2014.
Full Text & Related Files:
Abstract: Video has emerged as a dominant medium for online education, as witnessed by millions of students learning from educational videos on Massive Open Online Courses (MOOCs), Khan Academy, and YouTube. The large-scale data collected from students' interactions with video provide a unique opportunity to analyze and improve the video learning experience. We combine click-level interaction data, such as pausing, resuming, or navigating between points in the video, and video content analysis, such as visual, text, and speech, to analyze peaks in viewership and student activity. Such analysis can reveal points of interest or confusion in the video, and suggest production and editing improvements. Furthermore, we envision novel video interfaces and learning platforms that automatically adapt to learners' collective watching behaviors.
Other Sources: http://juhokim.com/files/CHI2014-Workshop-Peaks.pdf
http://www.eecs.harvard.edu/~kgajos/papers/2014/kim14leveraging.pdf
Terms of Use: This article is made available under the terms and conditions applicable to Open Access Policy Articles, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#OAP
Citable link to this page: http://nrs.harvard.edu/urn-3:HUL.InstRepos:22719144
Downloads of this work:

Show full Dublin Core record

This item appears in the following Collection(s)

 
 

Search DASH


Advanced Search
 
 

Submitters