Self-Regulated Learning increases the effectiveness of education and self-control has a high impact on the successful life generally. Cognitive biases heavily influence the decision making process, often against interests of those who make them. Therefore technological solutions that would support meta-cognitive scaffolding of learners may be very helpful. Our approach is based on Personal Learning Environments that provide both reflection and recommendation facilities. Preliminary results suggest that it can be a promising solution. Nevertheless, there are still challenges to be addressed, especially regarding the evaluation of this type of learning and supporting tools.
1. Advanced Community Information Systems Group
Chair for Information Systems and Databases
Prof. Dr. M. Jarke
Scaling up Technologies
for Informal Learning in
SME Clusters
Responsive Open
Learning Environments
Business perfOrmance
imprOvement through
individual employee
Skills Training
Self-Regulated Learning Nudges
Miloš Kravčík, Ralf Klamma
Miloš Kravčík, Ralf Klamma (2014). Self-Regulated Learning Nudges. International Workshop on Decision Making and Recommender Systems. Bolzano, Italy, September 18-19, 2014.
Motivation
Self-Regulated Learning (SRL)
includes one’s control over own cognitive and meta-cognitive activities
SRL depends on personal decisions
SRL can be influenced by recommendations
Problem
Changing preferences of humans
Long-term aims vs. instant gratification
Cognitive biases – the power of context
Balance between
Freedom of choice – motivation
Guidance – effectiveness
Solution
Integration of
Personal Learning Environments – flexibility
Recommender Systems – providing nudges (alert behaviour in a predictable way, easy to avoid)
Learning Analytics – supporting reflection
Evaluation
Outcomes: behavioural changes have limits and require long term research
Issues
short term: usability, workload, learning outcome
mid term: adoption of SRL – qualitative evaluation
long term: adoption of SRL – quantitative evaluation
Technology
ROLE Project: Responsive Open Learning Environments
http://www.role-project.eu/
ROLE Sandbox
http://role-sandbox.eu/
ROLE Widget Store
http://www.role-widgetstore.eu/
ROLE Software Development Kit
https://github.com/rwth-acis/ROLE-SDK
ROLE: SRL Process Model
ROLE: PLE with Nudges for SRL
Nussbaumer, A., Kravcik, M., Renzel, D., Klamma, R., Berthold, M., & Albert, D. (2014). A Framework for Facilitating Self-Regulation in Responsive Open Learning Environments. arXiv preprint arXiv:1407.5891.
Nussbaumer, A., Dahrendorf, D., Schmitz, H. C., Kravčík, M., Berthold, M., & Albert, D. (2014). Recommender and guidance strategies for creating personal mashup learning environments. Computer Science and Information Systems, 1(11).
Kravčík, M., & Klamma, R. (2011). On psychological aspects of learning environments design. In Towards Ubiquitous Learning (EC-TEL).
Cognitive Biases: Framing Effect
Source: D. Renzel
Source: M. Berthold
Identification of Learning Phases
Krenge, J., Petrushyna, Z., Kravcik, M., & Klamma, R. (2011). Identification of learning goals in forum-based communities. 11th IEEE International Conference on Advanced Learning Technologies (ICALT).
Nudges
Learning Analytics
Weeks
40% of „footprints“ align with SRL process model – potential for improvement
Users
Phase 1 & 2: low sentiment, questioner, lot of intents
Phase 3: increasing sentiment, conversationalist
Phase 4: high sentiment, answering person
URCH Discussion forums: preparation for tests in English language
Social Network Analysis: patterns of behavior from user relations
Intent Analysis: classification of goals from content
Sentiment Analysis: detecting subjective information from content
Workplace Learning Projects
Learning Layers
http://learning-layers.eu/
BOOST
http://www.boost-project.eu/
Kravcik, M., & Klamma, R. (2012). Supporting Self-Regulation by Personal Learning Environments. 12th IEEE International Conference on Advanced Learning Technologies (ICALT).