Part of a panel discussion at Learning Analytics and Knowledge 2014 - LAK14 - in Indianapolis.
This presentation contains the first and last sections of the panel discussion.
Faculty Profile prashantha K EEE dept Sri Sairam college of Engineering
Setting learning analytics in context
1. Setting learning analytics in
context: overcoming the
barriers to large-scale
adoption
Rebecca Ferguson, Doug Clow
Shane Dawson, Leah Macfadyen
Shirley Alexander, Alfred Essa
LAK14: Indianapolis
2. “The many elements
of the „TEL Complex‟
must all be taken into
account as an
innovation is
designed, developed
and embedded”
Scanlon, E., Sharples, M., Fenton-
O'Creevy, M., Fleck, J., Cooban, C.,
Ferguson, R., Cross, S., Waterhouse,
P. (2013). Beyond Prototypes. London:
TEL Research Programme.
5. Data wrangling
at The Open University
Rebecca Ferguson
The Open University, UK
LAK14: Indianapolis
6. Disparate data
VLE (Moodle) data
Survey data
Help desk data
Library data
Assessment data
Registration data
250,000 students around the world
Faculty expertise
Learning design
Learning outcomes
Assessment strategy
Module connections
Resource understanding
Data
Wranglers
Tacit knowledge
7. Talking the same language
Resource page? Sub page? URL?
Significance of dates?
9. Agreeing on conventions
80% agreed or strongly agreed that….
Is that
80% of registered students?
80% of those who completed the survey?
80% of those who completed both survey and course?
Or is it
80% of survey respondents who completed the
course and did not select „not applicable‟
10. Thinking through ethical issues
Support, not surveillance
Reporting at module level, not individual level
Survey responses kept apart from activity data
Making data accessible, not overwhelming
Negotiating meaning, not dictating interpretation