Keynote at the Web Science Summer School, Hannover, 30-07 to 04-08-2018

1. Web Analytics for
Everyday Learning
Mathieu d’Aquin - @mdaquin
Data Science Institute - datascienceinstitute.ie
National University of Ireland Galway
Insight Centre for Data Analytics
AFEL project (@afelproject)

2. Web Analytics (the weird great uncle of web science)

3. Web Analytics
Website or online system
Site owner
Web users
activities
analysis
Web user
Website or online system
activities analysis
Personal Analytics

4. Personal analytics: What for?
- To find ways to improve your behaviour (self-tracking,
quantified self)
- For transparency on security and privacy (privacy mirror,
translucent systems)
- To learn from it
d’Aquin, Thomas (2012) Consumer Activity Data: Usages and Challenges - http://kmi.open.ac.uk/publications/pdf/kmi-12-03.pdf

5. Example: Stephen Wolfram
Email data. From
http://blog.stephenwolfram.com
/2012/03/the-personal-analytics
-of-my-life/

6. Example: UCIAD and MOLUTI projects
Personal analytics dashboard of activities of
one student on their university’s systems
MOLUTI - browser extension showing basic
dashboard of browsing activities in the browser
d'Aquin, Elahi, Motta. "Semantic technologies to support the user-centric analysis of activity data." SPOT@ISWC 2011.

7. Example: Going broader than the browser
d'Aquin, Thomas (2013) "Semantic Web Technologies for Social Translucence and Privacy Mirrors on the Web." In PrivOn@ ISWC. 2013.

8. Example: Going broader than the browser

9. Example: Going broader than the browser
d'Aquin, Elahi, Motta. "Personal monitoring of web information exchange: Towards web lifelogging." WebSci 10.

10. Example: EPIFABO

11. Example: EPIFABO
d'Aquin, Thomas (2013) "Modeling and Reasoning Upon Facebook Privacy Settings." ISWC 2013 Demo.

13. Learning Analytics
Website or online system
Site owner
Web users
activities
analysis
Web user
Website or online system
activities
analysis for
learning
Personal Learning Analytics
University systems
Students
Course
manager
Learner

14. Examples of Learning Analytics
Vital for doctors OU Analyse

15. Applications - Recommendation

16. Example of Learning Analytics: Recommendation

17. Learning
(from a system’s point of view)
Learner
Platform
VLE | Website | Library
Assessment | Enrollment
School/University

18. Learning
(still from a system’s point of view)
Learner
Platform
VLE | Website | Library
Assessment | Enrollment
School/University

19. Objective: To create theory-backed methods and tools supporting self-directed
learners and the people helping them in making more effective use of online resources,
platforms and networks according to their own goals.
d'Aquin, et al. (2018). AFEL-Analytics for Everyday Learning. In Companion Proceedings of the The Web Conference 2018

20. Scenario
Jane is 37 and works as an administrative assistant in a local medium-sized company. As a hobbies, she enjoyed sewing and cycling in the local
forests. She is also interested in business management, and is considering either developing in her current job to a more senior level or making a
career change.
Jane spends a lot of time online at home and at her job. She has friends on facebook with whom she shares and discusses local places to go biking,
and others with whom she discusses sewing techniques and possible projects, often through sharing youtube videos.
Jane also follows MOOCs and forums related to business management, on different topics. She often uses online resources such as Wikipedia and
online magazine on the topics. At school, she was not very interested in maths, which is needed if she want to progress in her job. She is therefore
registered on Didactalia, connecting to resources and communities on maths, especially statistics.
Jane has also decided to take her learning seriously: She has registered to use the AFEL dashboard through the Didactalia interface. She has also
installed the browser extension to include her browsing history, as well as the facebook app. She has not included in her dashboard her emails, as
they are mostly related to her current job, or twitter, since she rarely uses it.
Jane looks at the dashboard more or less once a day, as she is prompted by a notification from the AFEL smartphone application or from the
facebook app, to see how she has been doing the previous day in her online social learning. It might for example say “It looks like you progressed
well with sewing yesterday! See how you are doing on other topics…”
Jane, as she looks at the dashboard, realises that she has been focusing a lot on her hobbies and procrastinated on the topics she enjoys less,
especially statistics. Looking specifically at statistics, she realises that she almost only works on it in Friday evenings, because she feels guilty of not
having done much during the week. She also sees that she is not putting as much effort into her learning of statistics as other learners, and not
making as much progress. She therefore makes a conscious decision to put more focus on it. She adds the dashboard goals of the form “to work on
statistics during my lunch break every week day” or “to have achieved a 10% progress compared to now by the same time next week”. The
dashboard will remind her how she is doing against those goals as she go about her usual online social learning activities. She also gets
recommendation of things to do on Didactalia and Facebook based on the indicators shown on the dashboard and her stated goals.

21. Scenario
Jane is 37 and works as an administrative assistant in a local medium-sized company. As a hobbies, she enjoyed sewing and cycling in the local
forests. She is also interested in business management, and is considering either developing in her current job to a more senior level or making a
career change.
Jane spends a lot of time online at home and at her job. She has friends on facebook with whom she shares and discusses local places to go biking,
and others with whom she discusses sewing techniques and possible projects, often through sharing youtube videos.
Jane also follows MOOCs and forums related to business management, on different topics. She often uses online resources such as Wikipedia and
online magazine on the topics. At school, she was not very interested in maths, which is needed if she want to progress in her job. She is therefore
registered on Didactalia, connecting to resources and communities on maths, especially statistics.
Jane has also decided to take her learning seriously: She has registered to use the AFEL dashboard through the Didactalia interface. She has also
installed the browser extension to include her browsing history, as well as the facebook app. She has not included in her dashboard her emails, as
they are mostly related to her current job, or twitter, since she rarely uses it.
Jane looks at the dashboard more or less once a day, as she is prompted by a notification from the AFEL smartphone application or from the
facebook app, to see how she has been doing the previous day in her online social learning. It might for example say “It looks like you progressed
well with sewing yesterday! See how you are doing on other topics…”
Jane, as she looks at the dashboard, realises that she has been focusing a lot on her hobbies and procrastinated on the topics she enjoys less,
especially statistics. Looking specifically at statistics, she realises that she almost only works on it in Friday evenings, because she feels guilty of not
having done much during the week. She also sees that she is not putting as much effort into her learning of statistics as other learners, and not
making as much progress. She therefore makes a conscious decision to put more focus on it. She adds the dashboard goals of the form “to work on
statistics during my lunch break every week day” or “to have achieved a 10% progress compared to now by the same time next week”. The
dashboard will remind her how she is doing against those goals as she go about her usual online social learning activities. She also gets
recommendation of things to do on Didactalia and Facebook based on the indicators shown on the dashboard and her stated goals.

22. Challenge #1: Collecting data
eLearning
platform (e.g.
moddle)
learner
analyst teacher
activities
generating
traces
traces and
metadata
resources and
metadata
analyse
learner
identifier
activities generating
traces, with (sometimes)
different identifiers
?analyse

23. browser
Challenge #1: Collecting data

24. browser
AFEL Data
Platform
Extension
app
Tracker
Crawler
Crawler
Traces and
metadata
AFEL
identifier
AFEL
identifier
Challenge #1: Collecting data

25. browser
AFEL Data
Platform
Analytics platform
VisualisationAFEL identifier
Analysis
Extension
app
Tracker
Crawler
Crawler
AFEL Core
Data Model
(based on
schema.org)
Learning
indicators
Traces and
metadata
AFEL
identifier
AFEL
identifier
Challenge #1: Collecting data
Integrated
personal data

26. Maximising what? Minimising what?
teacher analyst
Ratio :
students’ success
cost in effort/resources
(?)
learner
In the context of informal,
self-directed learning, what
is success?
What are the relevant
notions of effort and cost?
Challenge #1: What is learning?

27. Cognitive model: Learning and knowledge
construction through co-evolution
The dynamic processes of learning and knowledge construction from
Kimmerle, Moskaliuk, Oeberst, and Cress, 2015.

28. Cognitive model: Learning and knowledge
construction through co-evolution
The dynamic processes of learning and knowledge construction from
Kimmerle, Moskaliuk, Oeberst, and Cress, 2015.

29. Cognitive model: Learning and knowledge
construction through co-evolution
The dynamic processes of learning and knowledge construction from
Kimmerle, Moskaliuk, Oeberst, and Cress, 2015.
“constructive friction is the driving force behind
learning” -- AFEL Deliverable 4.1, [CK08]

30. Identified types of constructive frictions, indicators of
learning (in a given learning scope)
- Coverage: Most obvious indicator. How much of the concepts
covered by the given learning scope (topic) have been covered by
captured learning activities.
- Complexity: How the learner difficult at the resources used by the
learner in exploring this learning scope.
- Diversity: How diverse the resources and activities used by the
learner have been in the given learning scope.

31. Example - coverage
Text analysis Clustering
Progress
analysis
Browser history
Learning scopes
(topics)

32. Example - coverage

33. Example - coverage

34. Example - coverage

35. Example - coverage
web programming
british isles
d'Aquin, et al. (2017) "AFEL: Towards Measuring Online Activities Contributions to Self-directed Learning." In ARTEL@ EC-TEL. 2017.

36. Results

37. Results

38. Results
See Analytics for Everyday Learning workshop at EC-TEL 2018

39. Conclusion
Web Science, including web analytics, social media analysis,
learning analytics, is mostly about what a lot of people do in a
limited context.
Personal (learning) analytics is about analysing what one
person does over a large variety of contexts, for their own
benefits (efficiency, self-improvement, privacy monitoring).
There are many technological challenges to achieve this.
There are also many non-technological challenges regarding
how we use this (transparency, self-governance, control, etc.)

40. Thank you!
@mdaquin
mathieu.daquin@nuigalway.ie
mdaquin.net
@afelproject
afel-project.eu