1. The document discusses learning analytics (LA), including what it is, examples of LA tools and projects, and stakeholder viewpoints.
2. Stakeholders like managers, teachers, and students have different views on how LA could be used to improve learning, teaching, and student outcomes.
3. Key concerns about LA include issues around resources, skills, privacy, and ensuring LA adds value and doesn't negatively stereotype or limit students.
Rapple "Scholarly Communications and the Sustainable Development Goals"
What can learning analytics do for us
1. What can learning analytics
do for us?
Yi-Shan Tsai
yi-shan.tsai@ed.ac.uk
@yi_shan_tsai
http://sheilaproject.eu/
RTEN seminar series
30 January 2019
2. What to expect…
• What is learning analytics (LA)
• Project overview
• Multi-stakeholder viewpoints on the pros and cons
• Implications for a learning analytics (LA) strategy
• SHEILA framework
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
5. Learning analytics is…
“the measurement, collection, analysis and reporting of data about
learners and their contexts, for purposes of understanding and
optimising learning and the environments in which it occurs” (Long et
al., 2011).
Long, P. D., Siemens, G., Conole, G., & Gašević, D. (Eds.). (2011). In Proceedings of the 1st International Conference on Learning Analytics and Knowledge (LAK’11). Banff, AB,
Canada: ACM.
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
8. Learning analytics examples
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Arnold, K. E., & Pistilli, M. D. (2012, April). Course Signals at Purdue: Using learning analytics to increase student success. In Proceedings of the 2nd International Conference
on Learning Analytics and Knowledge (pp. 267-270).
Goal: address retention
Predictive algorithm:
-Performance
-Effort
-Prior academic history
-Student characteristics
11. Learning analytics examples
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Learning Analytics Report Card (LARC)
http://larc-project.com
Involve students in critical conversations
around the use of their data for
computational analysis in education.
Knox, J. (2017). Data Power in Education: exploring critical awareness with the ‘Learning Analytics
Report Card’ (LARC). Special Issue: Data Power in Material Contexts, Journal of Television and
Media. http://journals.sagepub.com/doi/full/10.1177/1527476417690029
Isard, A. and Knox, J. 2016. Automatic Generation of Student Report Cards. 9th International Natural
Language Generation conference. Edinburgh, Sept 5-8
http://www.macs.hw.ac.uk/InteractionLab/INLG2016/proceedings/pdf/INLG33.pdf
13. Learning analytics is…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Clow, D. (2012, April). The learning analytics cycle: closing the loop effectively. In Proceedings of the 2nd international conference on learning analytics and knowledge (pp. 134-138). ACM.
15. Objectives
• Understand the state of the art
• Engage key stakeholders directly
• Develop a policy framework
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
17. Challenges in institutional
adoption of LA
Literature review
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
Tsai, Y. S., & Gasevic, D. (2017). Learning analytics in higher education – challenges and policies: a review of eight learning analytics policies. In Proceedings of the
Seventh International Learning Analytics & Knowledge Conference (pp. 233-242).
19. 2. Unequal engagement with primary stakeholders
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
https://pixabay.com/
20. 3. Gaps in data literacy across stakeholders
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
https://pixabay.com/
21. 4. Weak grounding of learning theories
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
https://pixabay.com/
22. 5. Little evidence demonstrating the impacts of LA-based
interventions
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
https://pixabay.com/
23. 6. Lack of institution-based polices for learning analytics
practices
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
http://sheilaproject.eu/
https://pixabay.com/
26. Managers would like learning analytics to…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• To improve student learning performance – 40 (87%)
• To improve student satisfaction – 33 (72%)
• To improve teaching excellence – 33 (72 %)
• To improve student retention– 26 (57 %)
• To explore what learning analytics can do for our
institution/ staff/ students – 25 (54 %)
Institutional survey
(n=46)
Tsai, Y.-S., & Gašević, D. (2017). The State of Learning Analytics in Europe – Executive Summary – SHEILA (Executive summary). Retrieved from http://sheilaproject.eu/2017/04/18/the-state-
of-learning-analytics-in-europe-executive-summary/
27. Managers would like learning analytics to…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• To provide personalised learning support (39 %)
• To increase learning motivations (37 %)
• To inform curriculum (35 %)
• To encourage self-regulated learning (30 %)
• To improve student-teacher communication (26 %)
• To improve student recruitment (24 %)
• Other (2 %)
Institutional survey
(n=46)
Tsai, Y.-S., & Gašević, D. (2017). The State of Learning Analytics in Europe – Executive Summary – SHEILA (Executive summary). Retrieved from http://sheilaproject.eu/2017/04/18/the-state-
of-learning-analytics-in-europe-executive-summary/
28. Institutional goals & approaches
• Interview data (27 institutions)
• Epistemic Network Analysis
(ENA)
• The concurrence of codes
implies the strength of
connection
• The frequency of code
concurrence is expressed by the
weight (thickness) of the lines
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Shaffer, D. W., Collier, W., & Ruis, A. R. (2016). A tutorial on epistemic network analysis: Analyzing the structure of connections in cognitive, social, and interaction data. Journal of Learning
Analytics, 3(3), 9-45.
29. Comparison by adoption experience
Less than one year One year or more
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
30. Teachers would like learning analytics to…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
STUDENT
LEVEL
TEACHER
LEVEL
PROGRAM
LEVEL
Take responsibility for their
learning and enhancing their
SRL- skills
Assess the degree of success to
prevent students from begin
worried or optimistic about
their performance
Method to identify student’s
weaknesses and know where
students are with their progress
Understand how students
engage with learning content
Improve of the design and
provision of learning materials,
courses, curriculum and support
to students
Understand how program is
working (strengths and
bottlenecks)
Improve educational quality
(e.g. content level)
Focus groups:
• 16 groups
• 4 universities
• 59 participants
31. Teachers would like learning analytics to…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Focus groups:
• 16 groups
• 4 universities
• 59 participants
Know the ‘usefulness’ of resources and the preferences
of students towards learning materials
Enable personalised support to second language
speakers
Evaluate the workload of students who were mostly
part-time learners
UK & Spanish FGs
Estonian FGs
Dutch FGs
32. Students would like learning analytics to…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Personalised
support
Feedback
Academic
resources
Teaching
quality
Focus groups:
• 18 groups
• 4 universities
• 74 participants
33. Desires for self-regulated learning
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Survey:
• 6 institutions
• 3053 returns
SRL:
• Receiving a complete
profile of their
learning
• Making their own
decisions based on
the analytics results
• Knowing how their
progress compares to
a set learning goal
34. High expectations of self-regulated learning
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Survey:
• 6 institutions
• 3053 returns
SRL:
• Receiving a complete
profile of their
learning
• Making their own
decisions based on
the analytics results
• Knowing how their
progress compares to
a set learning goal
35.
36. Managers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Returns on
investment
Resources
Culture Skills
37. Returns on investment…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“We could have had a little black box instead of an expensive piece of
software. The wrapping around the project, the energy, the
commitment, the targeted actions, how much of that would have just
delivered some change anyway?” – Manager
38. Returns on investment…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“Learning analytics is at an early stage and so over time it may be able
to do a lot more things than we can do now. In fact, it will but there is
this problem that if things don’t deliver what people expect quickly,
they then say, ‘oh there’s no point in doing that’, and it gets a bad
name.” – Manager
39. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Students
Teachers
Learning
analytics
40. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Student-level
https://www.pinterest.com/pin/432486370448743887/
41. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Student-level
https://www.pinterest.com/pin/432486370448743887/
42. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Student-level
https://www.pinterest.com/pin/432486370448743887/
43. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Teacher-level
https://www.pinterest.com/pin/432486370448743887/
44. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Teacher-level
https://goo.gl/images/cA7J3h
45. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Learning analytics-level
https://goo.gl/images/TK6J8p
Can individual
differences be
captured?
46. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
• Learning analytics-level
https://goo.gl/images/TVLukx
Interpretations of
learning vary
47. Teachers are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“I don’t want it [LA] to make all of the students behave in the exact
same way to satisfy an algorithm. I want it to enable students to have
the best experience in whatever that experience is. You know, you can
be totally different from everyone else and still do perfectly fine. I want
it [LA] to…enable students to do better and not make them all mini
‘me’s.” - Teacher
48. Students are concerned about…
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Privacy Stereotypes
Learning being
quantified
Losing human
contacts
49. http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“Although consumers seem to be concerned
about their privacy as reflected in their
intentions to disclose (e.g., measured via
‘‘willingness to provide information’’),
anecdotal evidence suggests their behaviors
diverge from their intentions to disclose
personal details.”
(Norberg, Horne, & Horne, 2007, p. 107)
Privacy
paradox
50. 1. Perceived benefits outweigh perceived risks
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“I haven’t been in University for so long, so for me to get back to the
school was challenging, and so for me with the personal tutor I don’t
mind sharing my data ‘cause she will help me to develop myself
further.” - Student
51. 2. Power imbalance
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“You have to agree to share this data otherwise you wouldn’t enrol, so
you are not probably thinking that much about consequences of every
single piece of data that you provide to the university. It’s just because
it’s a part of the process of application.” - Student
52. 3. Trust exacerbates information asymmetry
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
“That [Data policy] is something I don’t think I would ever focus on or
look for, so I honestly don’t know. It could be out there and I could
maybe Google it, and it would be on a page somewhere if I wanted to
find it.” - Student
53. Implications for LA strategy
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
54. 1. A sound policy and effective
communication
Purpose, access, anonymity, and security
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
55. 2. Increase the observability and
trialability of LA to attract buy-in
An incremental approach
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
56. 3. Install data literacy and
reflective skills among key
stakeholders
Moving from data to action
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
57. 4. Incorporating the views of
different stakeholders to develop a
common vision and a sense of
ownership
A dialogic approach
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
58. 5. Clarify the value of LA within
its limitations
Expectation management
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
59. SHEILA framework
Action, challenges, and policy
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
60. http://sheilaproject.eu/sheila-framework/
Tsai, Y. S., Moreno-Marcos, P. M., Jivet, I., Scheffel, M.,
Tammets, K., Kollom, K., & Gašević, D. (2018). The
SHEILA Framework: Informing Institutional Strategies
and Policy Processes of Learning Analytics. Journal of
Learning Analytics, 5(3), 5-20.
http://sheilaproject.eu/
Learning analytics (LA) SHEILA project Stakeholder views Implications for LA strategy SHEILA framework
Editor's Notes
Learning today often takes place in a hybrid environment – a combination of online and offline settings.
In a traditional classroom, we observe how students are doing with their studies through direct interactions in the class and evaluations of their assignments or exams. Today, the shift of learning to the online setting means classroom observations are no longer sufficient. Meanwhile, the advancement of technology means it is possible for us to collect a wide range of digital data from students’ interactions with the learning environments, e.g., log-ins, access time, length of time spent. Learning analytics analyses the data by looking for patterns.
A 3-year pilot project with Civitas Learning started in 2016 to investigate student engagement in the digital learning environments. The project serves a strategic purpose to gain experience of developing learning analytics models and develop a Learning Analytics Policy.
Signals is based on predictive models. The purpose is to determine in real time which students might be at risk, partially indicated by their effort within a course.
Interventions may be: Posting of a traffic signal indicator on a student’s LMS home page; • E-mail messages or reminders; • Text messages; • Referral to academic advisor or academic resource centers; or, • Face to face meetings with the instructor.
A 3-year pilot project with Civitas Learning started in 2016 to investigate student engagement in the digital learning environments. The project serves a strategic purpose to gain experience of developing learning analytics models and develop a Learning Analytics Policy.
To close the feedback loop
The project does not deal with technical issues but socio-cultural issues around LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
Following the literature review, we carried out a series of research activities to get a better understanding of the identified challenges and other factors that influence the adoption of LA.
A survey question (multiple choices) provided 11 options for motivations specific to learning and teaching. 46 from 22 countries
responded (response rate: 15%).
The top 4 are strongly associated with institutional KPIs
By contrast, only the ‘improving student recruitment’ option is more directly linked to institution KPIs. Perhaps managers do not see a close link between this and LA.
Institutional goal: Goals set for LA are to improve institutional performance or management. LA will influence decisions made by senior managers.
Teaching goal: Goals set for LA are to inform teaching and support. LA is to will influence decisions made by teachers.
Learning level: Goals set for LA are to improve learning and student experience. LA is to will influence decisions made by students.
These connections suggest that institutions or projects that set out to improve institutional performance through LA tended to have identified clear problems to solve, e.g., student retention issues. By contrast, institutions or projects that aimed to use LA to inform teaching and student support had a stronger focus on exploring a phenomenon, e.g., how students engage with learning resources.
For novice institutions, LA was often adopted as a measuring tool for institutional performance, e.g., student retention rate. By contrast, more experienced institutions showed strong connections between teaching-level goals and exploratory approaches . Though institutional goal dominates, there is a shift of focus towards teaching and learning.
Provision of timely feedback, easy access to digital resources, and personalised learning support
Even though the average responses tended to be similar across locations, the sample of students from the Open University of the Netherlands were found to have lower ideal expectations towards receiving complete profiles across modules based on LA, compared to the other samples. This highlights that there is no one-size-fits-all LA solution, and further investigation into the preference of students towards the access to their learning data at this particular institution is needed.
U19
U1
How data is collected, analysed and interpreted affects our intrepretations of learning
Students expressed protective attitudes of personal data, but the described actions that they’ve taken to protect their personal data showed the contrary.
Trust plays a role here.
Five attributes of innovations: relative advantage, compatibility, complexity, trialability, observability
- Rogers, Everett. M. (2010). Diffusion of innovations. Simon and Schuster.