The document discusses research on gaining insights about MOOC learners by analyzing their activities on social web platforms. It identifies specific platforms where a significant fraction of learners can be traced and explores how learner traits influence their MOOC preferences. The findings indicate that, on average, 5% of MOOC learners can be identified across five popular social platforms, revealing behavioral patterns before, during, and after course participation.

1. Beyond the MOOC platform:
Gaining Insights about Learners
from the Social Web
Guanliang Chen, Dan Davis, Jun Lin,
Claudia Hauff, Geert-Jan Houben
Web Information Systems, TU Delft

2. Whythis research?
Learner
Engagement, retention, …
During MOOC

3. Whythis research?
Learner
Before MOOC
NOTHING
Engagement, retention, …
During MOOC

4. Whythis research?
Learner
Before MOOC
NOTHING
Engagement, retention, …
During MOOC
NOTHING
After MOOC

5. Howto solve the problem?
We propose:
a deeper understanding about learners
can be gained by exploring their traces
in the Social Web.

6. Whatresearch questions?

7. Whatresearch questions?
1
On what Social Web platforms can a significant fraction of
MOOC learners be identified?

8. Whatresearch questions?
1
On what Social Web platforms can a significant fraction of
MOOC learners be identified?
Are learners who demonstrate specific sets of traits
on the Social Web drawn to certain types of MOOCs? 2

9. Whatresearch questions?
1
On what Social Web platforms can a significant fraction of
MOOC learners be identified?
Are learners who demonstrate specific sets of traits
on the Social Web drawn to certain types of MOOCs? 2
To what extent do Social Web platforms enable us to
observe (specific) user attributes
that are highly relevant to the online learning experience?
3

10. Learner Identification
across Social Web platforms
edX learners
Email Login name Full name+ +

11. Learner Identification
across Social Web platforms
edX learners
Email Login name Full name+ +
1. Explicit Matching
Profile images & links
Identification via
emails

12. Learner Identification
across Social Web platforms
edX learners
Email Login name Full name+ +
1. Explicit Matching
Profile images & links
Identification via
emails
2. Direct Matching
Identification via profile
links from Step 1

13. Learner Identification
across Social Web platforms
edX learners
Email Login name Full name+ +
1. Explicit Matching
Profile images & links
Identification via
emails
2. Direct Matching
Identification via profile
links from Step 1
3. Fuzzy Matching
Search learners by their
login & full names
Compare:
1. profile link
2. profile image
3. login & full names

14. Learner Identification
across Social Web platforms
edX learners
Email Login name Full name+ +
1. Explicit Matching
Profile images & links
Identification via
emails
2. Direct Matching
Identification via profile
links from Step 1
3. Fuzzy Matching
Search learners by their
login & full names
Compare:
1. profile link
2. profile image
3. login & full namesMATCH !

15. Social Web platforms
involved in our work

16. Matching Results
for 18 DelftX MOOCs
Lowest Highest Overall
Gravatar 4,37% 23,49% 7,81%
Twitter 4,99% 17,58% 7,78%
Linkedin 3,90% 11,05% 5,89%
StackExchange 1,23% 21,91% 4,58%
GitHub 3,43% 41,93% 10,92%

17. Matching Results
for 18 DelftX MOOCs
Lowest Highest Overall
Gravatar 4,37% 23,49% 7,81%
Twitter 4,99% 17,58% 7,78%
Linkedin 3,90% 11,05% 5,89%
StackExchange 1,23% 21,91% 4,58%
GitHub 3,43% 41,93% 10,92%
On average, 5% of learners can be identified on globally
popular Social Web platforms.

18. Learners on
Twitter
- To predict learners’ demographics (e.g., age & gender)

19. Learners on
Linkedin
- Using skills to characterise learners
- Visualised by applying t-SNE techniques.

20. Learners on
StackExchange
- Functional
Programming
learners in
StackOverflow
- To what extent do
learners change their
question/answering
behaviour during
and after a MOOC?

21. Learners on
GitHub
- To what extent do learners transfer their acquired
knowledge into practice?
- Functional Programming learners

22. Take-home
Messages
On average, 5% of learners from 18 DelftX MOOCs
can be identified on 5 globally popular Social Web platforms. 1

23. Take-home
Messages
On average, 5% of learners from 18 DelftX MOOCs
can be identified on 5 globally popular Social Web platforms. 1
Learners with specific traits prefer different types of MOOCs.2

24. Take-home
Messages
On average, 5% of learners from 18 DelftX MOOCs
can be identified on 5 globally popular Social Web platforms. 1
Learners with specific traits prefer different types of MOOCs.2
Learners’ post-course behaviour can be investigated
by using their external Social Web traces.3

25. http://bit.ly/wis-learning-analytics
Thanks for your
participation!