mobile icon

AFEL – Analytics for Everyday Learning

Working groupKnowledge Construction Lab
Duration12/2015 - 11/2018
FundingEU research and innovation programme 'Horizon 2020' (687916)
Project description

The research project AFEL (Analytics for Everyday Learning) was funded by the EU research and innovation programme 'Horizon 2020' and aimed at investigating the processes of learning and knowledge construction on the internet. Psychologists, psycholinguists, data scientists, and software engineers worked together to develop tools to support these online learning processes.

The goal of the project was to develop methods and tools to understand informal/collective learning as it surfaces implicitly in online social environments. While Learning Analytics and Educational Data Mining traditionally rely on data from formal learning environments, studies have for a long time demonstrated that learning activities happen for a large part online, in a variety of other platforms. The aim of AFEL was therefore to devise the tools for exploiting learning analytics on such learning activities, in relation to cognitive models of learning and collaboration that are necessary to the understanding of loosely defined learning processes in online social environments.
To achieve this, AFEL gathered a range of skills in a consortium funded by the EU Horizon 2020 programme including experts in data analytics, interaction with data, cognitive models of learning and collaboration, as well as the developers of online social platforms. Concretely, the objectives of this consortium were to 1) develop the tools necessary to capture information about learning activities from online social environments; 2) create methods for the analysis of such informal learning data, based on combining visual analytics with cognitive models of learning and collaboration; and 3) demonstrate the potential of the approach in improving the understanding of informal learning, and the way it can be better supported. For example, recommender systems can be used to recommend usable learning materials for online-learners. Dynamic network visualizations provided them with feedback on their learning contents and helped them to avoid acquiring biased knowledge.


Knowledge Media Institute KMI, The Open University in Milton Keynes (UK)

L3S, Leibniz University Hannover (DE)


KNOW Center, TU Graz (AT)


Yenikent, S., Holtz, P., Thalmann, S., d'Aquin, M., & Kimmerle, J. (in press). Evaluating the AFEL learning tools: Didactalia users’ experiences with personalized recommendations and interactive visualizations. 13th European Conference on Technology Enhanced Learning Heidelberg, Dordrecht, London, New York: Springer.

Holtz, P. Fetahu, B., & Kimmerle, J. (2018). Effects of contributor experience on the quality of health-related Wikipedia articles. Journal of Medical Internet Research, 20:e171.

Yenikent, S., Buttliere, B., Fetahu, B., & Kimmerle, J. (2018). Wikipedia article measures in relation to content characteristics of lead sections. In S. Dietze, M. d'Aquin, D. Gasevic, E. Herder, & J. Kimmerle (Eds.), 7th International Workshop on Learning and Education with Web Data (#LILE2018) in conjunction with the 10th ACM Conference on Web Science (WebSci18) (pp. 5-8). Amsterdam, The Netherlands: Association for Computing Machinery.

Yenikent, S., Holtz, P., & Kimmerle, J. (2017). The impact of topic characteristics and threat on willingness to engage with Wikipedia articles: Insights from laboratory experiments. Frontiers in Psychology, 8:1960.