Sense-making from Learning Analytics: Exploring Challenges and Opportunities
This collection of images delves into the realm of learning analytics, emphasizing the complexities of sense-making and the challenges faced. It discusses the interpretation of granular behavioral measures, the role of proxies in understanding behavior, and the importance of selecting well-supported metrics with known theoretical relations for effective sense-making. By exploring topics such as data reliability, spurious correlations, and video complexity, the content sheds light on the diverse facets of analyzing and deriving meaning from learning analytics data.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. Download presentation by click this link. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
E N D
Presentation Transcript
Sense-making from learning analytics Frans van der Sluis f.van.der.sluis@fgga.leidenuniv.nl
Some learning analytics Granular analyses Big predictions Clicks Perceived difficulty Seek actions Dropouts Video length Engagement Guo (2014): 6 minutes length optimal for engagement
Dwelling time might seem straightforward, but its interpretation is not.
Our study Shows that Video complexity can increase but also decrease dwelling time More variables are needed to explain dwelling time Dwelling rate and time are not directly interpretable and as such cannot function as a proxy measure of (perceived) difficulty nor of other related constructs.
Some challenges Reliability and repeatability Data-driven Spurious correlations Validity Proxies of behaviour Construct validity
From learning at scale To learning about learning
On sense-making (1) It is difficult to unambiguously assign meaning to granular measures of behaviour
On sense-making (2) Any interpretation of a proxy of behaviour becomes plausible once controlling for related variables - such as video complexity - that are theoretically expected to explain it.
On sense-making (3) To allow for sense-making from learning analytics, it is critical to select well-supported metrics with known theoretical relations.
