Engaging Learning Analytics in MOOCs: the good, the bad, and the ugly
9. Jun 2016•0 gefällt mir
1 gefällt mir
Sei der Erste, dem dies gefällt
Mehr anzeigen
•3,109 Aufrufe
Aufrufe
Aufrufe insgesamt
0
Auf Slideshare
0
Aus Einbettungen
0
Anzahl der Einbettungen
0
Downloaden Sie, um offline zu lesen
Melden
Bildung
Khalil, M., Taraghi, B., & Ebner M. (2016). Engaging Learning Analytics in MOOCs: the good, the bad, and the ugly. In proceedings of the International Conference on Education and new Developments.
Where is our research Department located...
our department
Educational Technology
TUGraz, Austria
OER
MOOCs
Learning AnalyticsPersonalized Learning
Big Data
Adaptive Learning
Educational Data Mining
Technology Enhanced Learning
Lifelong Learning
Learning Analytics
Analysis &
Interpretation
Lackner, E., Khalil, M., Ebner, M. “How to foster forum discussions within MOOCs: A case study”, IJARE (in review).
Khalil, M., Ebner, M. (2016). “What Massive Open Online Course (MOOC) Stakeholders Can Learn from Learning
Analytics?”. Learning, Design & Technology. Springer International Publishing.
How does it look like?
Source: BME Solutions Ltd
iMooX Learning Analytics (iLAP)
The Good
X 9
The Bad
X 6
The Ugly
X 4
Learning Analytics of MOOCs ...
The GOOD
▸Prediction (... students at risk, performance...)
▸Recommendation (... suggest course, article...)
▸Visualization (... dashboards, plots...)
▸Entertainment (... Gamification elements...)
9
The GOOD
▸Benchmarking (... evaluate courses, difficulties...)
▸Personalization (... customize courses, notes...)
▸Enhance Engagement (... interventions for
subpopulations...)
▸Communicate Information (... statistical
analysis to different stakeholders…)
▸Cost Saving (... allocate resources effectively...)
9
The Bad
▸Security
○ Students Database security configuration is overlooked.
○ Achieve confidentiality, integrity, and availability.
▸Privacy
○ MOOC datasets may hold sensitive information.
○ Considered as a threat and constraint.
▸Ownership
○ Who owns the collected data?
6
The Bad
▸Consent
○ Declaration on data collection
○ Processed data usage, sell to third parties or research?
▸Transparency
○ Transparent of research or data usage
▸Storage
○ Storing big data can be costly and complex
○ European Directive 95/46/EC says personal data needs to
be stored no longer than necessary.
6
The Ugly
▸False Positives
○ Decisions based on small subset of data.
○ Forums activity as an example!
▸Fallacy Analytics
○ Analytics could fail!
○ Wrong predictions, interventions, visualizations...
▸Bias
○ Bias towards certain hypothesis leads to biased LA
▸Distill meaningful data
○ Pay efforts for ineffective results
4