Friday, October 08, 2010

Why we need big, authentic datasets for education?

In the world of consumer recommender systems, it is a common practise to use different data sets as benchmarks to evaluate new recommender systems algorithms (e.g. MovieLens, Book-Crossing, EachMovie data set).

In TEL, there are no standardised data sets publicly available, so that the outcomes of different recommender systems within TEL are hardly comparable.


**********************************************
CALL FOR CONTRIBUTIONS

Workshop: dataTEL- Data Sets for Technology Enhanced Learning
Date: March 30th to March 31st, 2011
Location: Ski resort La Clusaz in the French Alps, Massif des Aravis
Funding: Food and lodging for 3 nights for 10 selected participants
Submissions: For being funded, please send extended abstracts to
http://www.easychair.org/conferences/?conf=datatel2011

Deadline for submissions: October 25th, 2010
**********************************************

1st workshop on ëData Sets for Technology Enhanced Learningí at the 2nd STELLAR Alpine Rendez-Vous in La Clusaz, France

SCOPE
Personalisation and analysis of user interaction data is a key approach to overcome the plethora of information in the knowledge society. It is expected that personalised learning has the potential to reduce delivery costs, to create more effective learning environments and experiences, to accelerate study time, and to increase collaboration between learners.

Recommender systems and information filtering are some of the promising technologies to support people in finding most suitable information and peer learners. They are increasingly applied in Technology-Enhanced Learning (TEL) in various European projects in order to personalise learning content and connect suitable peer learners according to their context (e.g., individual needs, preferences, and learning goals).

In the world of consumer recommender systems, it is a common practise to use different data sets as benchmarks to evaluate new recommender systems algorithms (MovieLens, Book-Crossing, EachMovie data set). In TEL, there are no standardised data sets publicly available, so that the outcomes of different recommender systems within TEL are hardly comparable.

So far, no universally valid knowledge exists on algorithm that can be successfully applied in a certain learning setting. Having such data sets could be a first major step towards a theory of personalisation within TEL that can be based on empirical experiments with verifiable and valid results.

Therefore, the objective of this workshop is to explore suitable data sets for TEL ñ with a specific focus on recommender and information filtering systems that can take advantage of these data sets. In this context, new challenges emerge like unclear legal protection rights and privacy issues, suitable policies and formats to share data, required pre-processing procedures and rules to create sharable data sets, common evaluation criteria for recommender systems in TEL and how a data set driven future in TEL could look like.

Relevant topics include, but are not limited to:
  • publicly available data sets for educational systems
  • dealing with legal protection rights towards data sets on a European level
  • privacy preservation for educational data sets
  • methods of effective anonymisation of educational data sets
  • management and pre-processing procedures for educational data sets
  • future scenarios for educational data sets
  • impact of educational data sets for learners and teachers
  • mash-ups based on educational data sets
  • recommender approaches that are based on educational data
  • evaluation methodologies and metrics for educational recommender systems

SUBMISSIONS
Authors are invited to submit original unpublished research as papers (4-8 pages). Demonstrations and Hands-on sessions are explicitly encouraged. All submitted papers will be peer-reviewed by at least three members of the program committee for originality, significance, clarity, and quality. Re-worked versions of accepted submissions will be published in the Interdisciplinary Journal of E-Learning and Learning Objects (IJELLO). In addition, the authors are asked to contribute short summaries of their submissions to the dataTEL group space at TELeurope to encourage early information sharing and discussion also with third persons.

Submission will be available through the EasyChair submission system:
http://www.easychair.org/conferences/?conf=datatel2011

All questions and submissions should be sent to: dataForTEL@gmail.com

WORKSHOP STRUCTURE
Based on workshop submissions, the organisers will identify 4 most pressing research challenges. For each of the challenges, we will allow around 2 hours discussion, started off through about two short submission presentations or keynotes. The final 2 hours of the last workshop day will be utilised to bring the results of the individual discussions together and to chart a vision of the future of TEL amplified by publicly available data sets.

FUNDING
Participants pay for their own travel and lodging. But we are able to fund food and lodging for 3 nights as well as the community event on Tuesday, March 29th for 10 participants. Please indicate your funding needs with your submission.

ORGANIZERS
Katrien Verbert (K.U.Leuven, BE)
Riina Vuorikari (European Schoolnet, BE)
Stefanie Lindstaedt (KnowCenter, AT)
Martin Wolpers (Fraunhofer Institute for Applied Information Technology, DE)
Miguel-Angel Sicilia (University of Alcal·, ES)
Nikos Manouselis (Greek Research and Technology Network, GR),
Hendrik Drachsler (Open University of the Netherlands, NL)


IMPORTANT DATES
Submission of extended abstract (1000-2000 words): October 25th, 2010
Notification of acceptance of abstracts: November 15th, 2010
Submission of papers: December 17th, 2011
Workshop: March 30th to March 31st, 2011

IMPORTANT WEBSITES
dataTEL group space: http://www.teleurope.eu/pg/groups/9405/datatel/
The Alpine Rendez-Vous: http://www.stellarnet.eu/programme/wp3/rendez-vous
La Clusaz: http://www.laclusaz.com/hiver-winter10/index.php?lang=_uk

VENUE DETAILS
The second STELLAR Alpine Rendez-Vous (ARV) will take place in the French Alps in the Massif des Arravis at a beautiful ski resort called La Clusaz (hotel Alpen Roc). There will be some free time in the afternoons for TEL community building during winter activities. Funding for lodging and food will be available for a limited number of participants.

THE ALPINE RENDEZ-VOUS
This 2011 STELLAR Alpine Rendez-Vous is the second event of a series. It is organized and funded by STELLAR, a European network of excellence on learning technologies (http://www.stellarnet.eu/). The ARV is not a standard conference, but a set of independent workshops located at the same time in the same hotel. Four workshops run in parallel during the first part of the week and four during the second part. It's called "Rendez-Vous" because shared events are organized in the middle of the week (Tuesday evening) and because we set up breaks and meals in a way that promotes informal encounters between participants from the different workshops. Finally, it is called "Alpine" because it gathers scientists in the Alps, away from their workplace routines, in a place where snow is used as social facilitator."