geistlogistic

Tutorial given at LAK13 conference, Leuven, April, 9th, 2013.

The presentation is informed by WP2 of the LinkedUp-project.eu that develops an Evaluation Framework for Open Web Data (Linked Data) Applications for Education purposes.

Drachsler, H., D’Aquin, M., Dietze, S., Herder, E., (2013). Evaluation of Linked Data Tools for Learning Analytics. Presentation given at Linked Data for Learning Analytics workshop at 3rd Learning Analytics and Knowledge Conference, Leuven, Belgium, 9th of April 2013.

First insights into a GCM study for the design a community agreed Evaluation Framework for the upcoming LinkedUp data competitions. The presentation was given for WP2 of the LinkedUp project at Elsevier HQ, Amsterdam. The Evaluation Framework also provides an interesting solution for standardising Learning Analytics research by comparing the results of different Applications in that domain.

Drachsler, H. & Stoyanov, S. (2013, 25th February). Design of an Evaluation Framework for Open Web Data Applications, Presentation given at the LinkedUp project meeting at Elsevier, Amsterdam, The Netherlands.

In December I was invited to give a presentation for the OUNL mamangement board on Open Science.

This presentation shows the vision of the Open University for Open Science in an elevator pitch format.

http://portal.ou.nl/documents/363049/ff7a3426-ce4a-4081-900d-f7d352046c62

http://creativecommons.org/licenses/by-nc-sa/3.0/

Drachsler, H. (2012, 06 December). Open Science. Open Universiteit Nederland, Heerlen, Netherlands.

We recently submitted the final version of a book on “Recommender Systems for Learning” (#RSFL) to Spinger (to appear soon in 2012) that focus on the past 10 years of research on recommender systems in technology-enhanced learning (TEL).

We introduced recommender systems and compared them to relevant work in TEL like adaptive educational hypermedia, learning networks, educational data mining and learning analytics. Then we emphasised on TEL as a recommendation problem, discussing how the recommendation problem is defined, which the recommendation goals are, and what the recommendation context usually covers as context.

We reviewed existing TEL datasets that may be used to support experimentation and testing, as well as discussed about how they can drive relevant research. We reported an extensive analysis of existing recommender systems that can be found in the literature for educational applications. And finally, we reflected on some major challenges that we see as important to be faced in the years to come, also outlining some potential directions of future research.

All the bibliography covered by this book is also available in an open Mendeley group with the same name “Recommender Systems for Learning“and will continue to be enriched with additional references. We would like to encourage the reader to sign up for this group and to connect to the community of people working on this topic, having access to the collected bibliography but also contributing pointers to new relevant publications within this very fast emerging research field.

The Dutch Higher Education Foundation -  SURF invited Wolfgang and me to a seminar on Learning Analytics, where we presented our Learning Analytics framework and a questionnaire that is build on top of it.
They brought some interesting parties from different educational institutions (schools -> universities) and some companies together.
One observations was that the companies mainly focus on business analytics for the educational sector and the management of an educational institute, whereas the educational designers and researchers tools presented to support students and teachers in improving learning and teaching.
That reminds me on the TEL recommender systems that were also applied in the beginning like in the MovieLens system and even used their datasets. They mainly recommended content from related persons without considering context of learners like learning goals or prior-knowledge levels to recommend peers, learning activities, or learning paths.

Wolfgang and I tried to paint the big picture of Learning Analytics with the framework and give some practical examples. Both parts of the audience (the companies and the educational institutes) found the framework rather useful to shape the goals of Learning Analytics applications.
What became clear from the educational institutes is that we need to provide solutions for the big players (Moodle, Blackboard or Sharepoint) when we want to run any experiments on Learning Analytics with them. Most of the educational providers in the Netherlands use one of these systems and any learning analytic tool needs to address them. Thus, after prototyping and having valuable outcomes you need to address one of the big systems to disseminate your learning analytic solutions to the stakeholder

Below you can find our presentation that received 650 clicks in 3 hours. That was really impressing. I received the following mail from slideshare:
“Turning Learning into Numbers – A Learning Analytics Framework” is being tweeted more than anything else on SlideShare right now. So we’ve put it on the homepage of SlideShare.net. 

Well done!

- SlideShare Team

Another indicator that Learning Analytics is a very hot topic.

Below you can find the presentation. Special thanks belong to Peter Kraker who provided us with his twitter visualization tool that enabled me to show some real time reflection examples of the seminar on Learning Analytics. Thanks Peter!

Here you can find the schedule of the 2 day dataTEL workshop at ARV2011. This time we will have two keynote speakers related to the dataTEL topics:

Shlomo Berkovsky (AU) and John Stamper (USA).

Shlomo Berkovsky is a Senior Research Scientist and Research Team Leader at the TLI project (CSIRO – Commonwealth Scientific and Industrial Research Organisation, Tasmanian ICT Centre). The project aims to provide individual users and their families with a personalized dietary and health information to help them to maintain a healthier lifestyle.
His research interests include user modeling and personalization. In particular, he is interested in recommender systems, collaborative and content-based filtering, mediation of user models, ubiquitous user modeling, context-aware personalization, personalized content generation, and use of machine learning and data mining techniques in user modeling and personalization.
Before joining CSIRO, he was a post-doctoral research fellow at the University of Melbourne. He graduated at the University of Haifa. The topic of my PhD was “Mediation of user models for enhanced personalization in recommender systems”.

John Stamper is the Technical Director of the Pittsburgh Science of Learning Center DataShop.  He is also a member of the research faculty at the Human-Computer Interaction Institute at Carnegie Mellon University.  His primary areas of research include Educational Data Mining and Intelligent Tutoring Systems.  John received his PhD in Information Technology from the University of North Carolina at Charlotte, holds an MBA from the University of Cincinnati, and a BS in Systems Analysis from Miami University.  Prior to returning to academia, John spent over ten years in the software industry.  John is a Microsoft Certified Systems Engineer (MCSE) and a Microsoft Certified Database Administrator (MCDBA). John was the co-chair of the 2010 KDD Cup Competition, titled “Educational Data Mining Challenge,” which centered on improving assessment of student learning via data mining.

On the 1st day Shlomo Berkovsky will give a keynote on: 

Setting Up a Data Contest
Abstract: Research contests have attracted attention in many areas, mainly due to their potential to boost research on a specific problem. Contests also facilitate a fair and objective evaluation means, as all the participants share the same data and task. This talk will focus on the details of organizing a research contest. Initially, we will overview several past contests: KDD Cup competition series, Netflix prize competition, and CAMRa challenge on context-aware recommendations. Then, we will discuss the essential components of a successful contest: selection of appropriate tasks, data processing and preparation, publicity and attraction of participants, and the logistics of carrying out the contest. Finally, we will spark the discussion on the upcoming I-KNOW dataTEL contest on predicting the performance of students with an intelligent tutoring system.

On the 2nd day John Stamper will give his keynote on:

DataShop: An Educational Data Mining Platform for the Learning Science Community
In this talk I will discuss my vision of creating a true platform for conducting educational data mining research. The talk will focus on DataShop, part of the Pittsburgh Science of Learning Center, which is an open data repository and set of associated visualization and analysis tools. DataShop has data from thousands of students deriving from interactions with on-line course materials and intelligent tutoring systems. The data is fine-grained, with student actions recorded roughly every 20 seconds, and it is longitudinal, spanning semester or yearlong courses. As of February 2011, over 245 datasets are stored including over 51 million student actions which equates to over 150,000 student hours of data. Most student actions are “coded” meaning they are not only graded as correct or incorrect, but are categorized in terms of the hypothesized competencies or knowledge components needed to perform that action. I plan to open the talk up as an interactive discussion in order
to answer questions related to some of the key issues we faced in developing an open data repository, including security, privacy, and data diversity.
Feel free to go to http://pslcdatashop.org to sign up for a free account and access DataShop prior to the workshop.

Based on the contributions of the participants we identified the following 4 most pressing topics of the workshop:
1. Topic: Evaluation of recommender systems in TEL
2. Topic: Data supported learning examples
3. Topic: Datasets from Learning Object Repositories and Web content
4. Topic: Privacy and data protection for dataTEL

We will tweet about the event and you are free to send you remarks by using the hashtag #datatel11.

Here you can find the detailed workshop schedule:

Besides presenting the Handover project in this presentation and the involvement of CELSTEC, we explain the evaluation approach we followed to create a customized Learning Network. The methodology offers a very effective set of evaluation tools  to customize a Learning Network to the needs of a target domain in this case health.

Presentation given at the CELSTEC, Learning Network plenary 22.03.2011.

Related articles

• Unleashing the Power of Networked Learning (blogs.hbr.org)
• Tribal Learning (relationship-economy.com)

Yesterday 3 Bachelor students of the computer science faculty of OUNL – Mark Rotteveel, Rene Quakkelaar, and Jan Blom Mark  presented the outcomes of their Bachelor project what was conducted in co-operation with our CELSTEC institute. The Team developed a very sophisticated MySQL wrapper for the NetLogo simulation environment that can easily be extended to other database systems.

It was the first Bachelor project that developed a system for an open source community what is very exciting because the actual lifetime of the project just begun with it’s release yesterday. The project will have an impact on the NetLogo project and NetLogo users all over the world what is a nice outcome of a Bachelor project.

The MySQL extension can be downloaded from http://code.google.com/p/NetLogo-sql. At this moment, the binary installation and the user manual are available. The source code and developer documentation will become available soon as well.

Some highlights of this extension:

• efficient use of connections by through a connection pooling library (BoneCP): accessing a database from a large number of agents is possible
• based on JDBC. This should make the addition of other databases than MySQL fairly easy
• well tested, both by continuous unit- and integration testing during development, and by adapting existing models (these models are not published as part of this project)
• the developers will continue to support and extend this extension for at least 1 year
• a version 1.1 with support for other open source databases (PostgreSql, perhaps others depend on the community), and with generic support for propriety databases (Oracle, MSSql Server, others) is planned and can be expected in a couple of months from now.

After the project presentation we discussed the impact of the project on NetLogo developments. Because using a database in NetLogo forces programmers to plan the simulation more intensively than without using a database. The database, tables, data types and so on need to be specified in advance like in other software projects. We also thought about a follow-up project with a graphical User Interface to design the underlying data structure and outputs the needed SQL code and the related NetLogo code file.

Yesterday, I gave a workshop on “How to use the Handover Toolbox to improve Handovers in Health”.  I presented a so called toolbox that is based on Elgg community portal and customized to the needs of the medical specialists to share knowledge to improve handover practice between General Practitioners and Hospitals. Most of the participants are not Web2.0 users so a lot of explanations and hands-on experiences were needed to disseminate the networked based learning ideas to the partners.

But the workshop was very fruitfully, we had very inspiring discussions on the future of training in health and the role of social networks. There will be some interesting Journal articles coming out of this cooperation. Below you can find the slides I used during the workshop.