SIG dataTEL aims to increasing research on educational datasets as it is expected that this will create more transparent, mutually comparable, trusted and repeatable experiments that lead to evidence-driven knowledge with approved indicators for theories in education and in particularly in TEL. Also see the overview slides on SlideShare.
Detailed description of the SIG
Technology Enhanced Learning (TEL) is undergoing a significant shift in paradigm towards more data driven systems that will make educational systems more transparent and predictable. Data science and data-driven tools will change the evaluation of educational practice and didactical interventions for individual learners and educational institutions. We summarise these developments under the keyword dataTEL that stands for ‘Data-Supported Technology-Enhanced Learning’.
Through the increasing application of learning management systems (LMS),intelligent tutoring systems (ITS), personal learning environments (PLE), Web 2.0 developments, and the EPUB3 standard1 the collection of large amounts of learning activity data becomes conventional. Although the TEL domain already stores data in
their e-learning environments automatically, it typically lacks research on TEL datasets.
The unused educational datasets offer an unexploited potential for the evaluation of educational interventions such as new learning settings, learning theories, and learning
technologies. A big advantage of the new dataTEL research is the possibility to collect educational data without any additional efforts like filling a questionnaire or conducting a pre- and post-test assessment; instead the learning activity data can be collected, analysed and reported on demand and therefore offers a new quality for the investigation of the phenomena ‘learning’. The collected learning activity data can be presented in real-time and according to the needs of different educational stakeholders like students, teachers, parents, institutions and decision makers. The representation of the learning activity data can support reflection and prediction processes of all stakeholders (students, teachers, and management) and therefore decrease the time that is needed to evaluate the effects of educational contents, scenarios, technology and more general educational interventions.
Furthermore, the increasing research on educational datasets will create more transparent, mutually comparable, trusted and repeatable experiments that lead to evidence-driven knowledge with approved indicators for theories in education and in particularly in TEL. Thus, educational datasets have the potential to facilitate a theory for TEL by providing constant evaluation and experiment settings to analyse learning. It can provide these constant evaluation settings for the whole spectrum of learning from formal to informal learning. Therefore, the educational datasets extend the methodological and empirical approaches to analyse learning and especially technology-enhanced learning that is still dominated by design-based research approaches, simulations, and field studies. The available educational data introduce an additional research paradigm to the TEL field that has the potential for new insights into learning processes by making so far invisible patterns in the data visible to researchers, educators and the learners.
Chairs of the SIG
Dr. Hendrik Drachsler (CELSTEC, Open University of the Netherlands)
Dr. Katrien Verbert (Dept. of. Computer Science, K.U.Leuven, Belgium)
- 2012 – Recommender Systems for Technology Enhanced Learning (RecSysTEL 2012)
- 2012 – Learning Analytics and Linked Data
- 2011 – dataTEL – Datasets for Recommender Systems in Technology-Enhanced Learning
- Link to the RecSysTEL book at Springer
Communication and knowledge exchange with participants
For communicating with members of the SIG the following tools are used:
- A Mendeley group is used for discussion and paper exchange with members of the group.