Data Sets as Facilitator for new Products and Services for Universities
1 like644 views
This document summarizes a presentation given by Dr. Hendrik Drachsler on using data sets to facilitate new educational products and services. The presentation discusses how data emerges from online interactions and can be used with recommender systems. It argues that while the field of technology enhanced learning collects plenty of data, it lacks shareable data sets that could enable more transparent, comparable experiments. Developing open educational data sets could support evaluating learning theories, comparing recommender systems, and creating new data-driven educational products and services.
Data Sets as Facilitator for new Products and Services for Universities
- 1. Dr. Hendrik Drachsler Centre for Learning Sciences and Technology @ Open University of the Netherlands Data Sets as Facilitator for new Products and Services for Universities 1 29.11.2010 VOR-ICT Bijeenkomst, Utrecht,The Netherlands
- 2. • Assistant Professor at the Learning Networks Program OUNL / CELSTEC • Research topics: Learning Networks, Technology Enhanced Learning, Recommender Systems, Personalisation, Mash-Ups and widget technology, Health2.0 2 Whoami
- 3. We live in a decade of industrial change Change picture 3
- 4. “The biggest challenge businesses face today is unlearning what was successful in the industrial age and learning how to prosper in the network era.” The challenge Jay Cross (2006) 4
- 5. Graphic by Alex Guerten, 2008 5
- 6. G L O B A L I S A T I O N LO C A L I S AT I O N Graphic by Alex Guerten, 2008 5
- 7. G LO C A L I S AT I O N Graphic by Alex Guerten, 2008 5
- 8. C O N S U M E R S P R O D U C E R S G LO C A L I S AT I O N Graphic by Alex Guerten, 2008 5
- 9. G LO C A L I S AT I O N P R O S U M E R S Graphic by Alex Guerten, 2008 5
- 10. http://flickr.com/photos/zoharma/97214235/sizes/l/by Zohar Manor-Abel 6 The Glocalisation / Prosumers world
- 18. Data emerge Johnson, S. (2001) 11
- 19. Data emerge Johnson, S. (2001) 11
- 20. Data emerge Johnson, S. (2001) 11
- 21. Data emerge Johnson, S. (2001) 11
- 22. Data emerge Johnson, S. (2001) 11
- 23. Data emerge Johnson, S. (2001) 11
- 24. Data emerge “We are leaving the age of information and entering the age of recommendation” Chris Anderson (2004) Johnson, S. (2001) 11
- 27. Recommender Systems People who bought the same product also bought product B or C … 12
- 28. The Long Tail 13Graphic Wilkins, D., (2009); Long tail concept Anderson, C. (2004)
- 29. The Long Tail 13Graphic Wilkins, D., (2009); Long tail concept Anderson, C. (2004) The Long Tail of Learning
- 30. TEL recommender are a bit like this... 14
- 31. TEL recommender are a bit like this... 14 We need to select for each application an appropriate recommender that fits its needs.
- 32. But... 15 Kaptain Kobold http://www.flickr.com/photos/ kaptainkobold/3203311346/ “The performance results of different research efforts in recommender systems are hardly comparable.” (Manouselis et al., 2010)
- 33. But... 15 Kaptain Kobold http://www.flickr.com/photos/ kaptainkobold/3203311346/ “The performance results of different research efforts in recommender systems are hardly comparable.” (Manouselis et al., 2010) The TEL recommender experiments lack transparency.They need to be repeatable to test: •Validity •Verification • Compare results
- 34. How others compare their their recommender systems 16
- 35. How others compare their their recommender systems 16 Although the TEL domain stores plenty of data everyday in e-learning environments (LMS, PLEs) it typically lacks shareable and publicly available data sets.
- 37. Promises of Open Data 18
- 38. Promises of Open Data 18
- 39. Promises of Open Data 18 Unexploited potentials:
- 40. Promises of Open Data 18 Unexploited potentials: • The evaluation of learning theories and learning technology
- 41. Promises of Open Data 18 Unexploited potentials: • The evaluation of learning theories and learning technology • More transparent, mutually comparable, trusted and repeatable experiments that lead to evidence-driven knowledge
- 42. Promises of Open Data 18 Unexploited potentials: • The evaluation of learning theories and learning technology • More transparent, mutually comparable, trusted and repeatable experiments that lead to evidence-driven knowledge • Development of new educational data products that combine different data sources in data mashups
- 43. New Science Paradigms 19 •Thousand years ago science was empirical (Describing natural phenomena) • Last few hundred years science: theoretical branch (Using models, generalizations) • Last few decades: computational branch (Simulating complex phenomena) • Nowadays: data science (Unify theory, experiment, and simulation, data captured by instruments and processed by software)
- 44. 20 Data Products
- 45. 20 Data Products
- 46. 21 Data Products
- 47. 21 Data Products
- 48. 21 Data Products Educational Data Products • Drop-out Analyzer • Group Formation Recommender • Question-Answering Tool •Awareness Tools
- 49. 21 Data Products Educational Data Products • Drop-out Analyzer • Group Formation Recommender • Question-Answering Tool •Awareness Tools
- 51. Beyond O P E N DATA 2348
- 53. Beyond O P E N DATAO P E N DATA 23 Beyond the 48
- 54. Beyond O P E N I N N OVAT I O NO P E N I N N OVAT I O N 23 Beyond the 48
- 55. Beyond VISUALIZATION OF DATAVISUALIZATION OF DATA 23 Beyond the 48
- 56. Beyond M A S H U P T E C H N O L O G YM A S H U P T E C H N O L O G Y 23 Beyond the 48
- 57. Beyond R E C O M M E N D E R S Y S T E M SR E C O M M E N D E R S Y S T E M S 23 Beyond the 48
- 58. Beyond P ROT E C T I O N R I G H T SP ROT E C T I O N R I G H T S 23 Beyond the 48
- 59. 24 Open Data
- 60. 24 Open Data
- 61. 24 Open Data
- 62. 24 Open Data
- 63. 24 Open Data
- 64. 24 Open Data
- 65. 24 Open Data
- 70. Open Innovation 26 R&D -> C&D
- 71. Open Innovation 26 R&D -> C&D
- 72. Open Innovation 26 R&D -> C&D
- 81. 3 Take away messages 30
- 82. 31
- 83. 31 Plan(t)ing for the future
- 84. 31 Plan(t)ing for the future 1. Use digital ecosystem services for student projects (Google API, Yahoo pipes, Twitter, Reuters Open Calais ...)
- 85. 31 Plan(t)ing for the future 1. Use digital ecosystem services for student projects (Google API, Yahoo pipes, Twitter, Reuters Open Calais ...) 2. Apply and create open data for research (Become part of the ecosystem, open innovation, science2.0 -> pre-processing, privacy protection)
- 86. 31 Plan(t)ing for the future 1. Use digital ecosystem services for student projects (Google API, Yahoo pipes, Twitter, Reuters Open Calais ...) 2. Apply and create open data for research (Become part of the ecosystem, open innovation, science2.0 -> pre-processing, privacy protection) 3. Empower your users to adjust and remix your contributions to the web (Open API’s, protocols, standards -> interoperability)
- 87. This silde is available at: http://www.slideshare.com/Drachsler Email: [email protected] Skype: celstec-hendrik.drachsler Blogging at: http://www.drachsler.de Twittering at: http://twitter.com/HDrachsler 32 Questions and ideas now or later...
- 88. References 33 Anderson, C. 2004.“The long tail.” Wired Magazine 12 (10).Available: http://www.wired.com/wired/archive/12.10/tail.html Cross, J., (2006) Informal learning: Rediscovering the natural pathways that inspire innovation and performance. Pfeifer Drachsler, H., Hummel, H., & Koper, R. (2008a). Personal recommender systems for learners in lifelong learning: requirements, techniques and model. International Journal of LearningTechnology 3(4), 404 - 423. Drachsler, H., Hummel, H., & Koper, R. (2008b). Using Simulations to Evaluate the Effects of Recommender Systems for Learners in Informal Learning Networks. Paper presented at the EC-TEL conference, 2nd Workshop on Social Information Retrieval in Technology Enhanced Learning (SIRTEL08). September, 16-19, 2008, Maastricht,The Netherlands: CEUR Workshop Proceedings Drachsler, H., Hummel, H., & Koper, R. (2009). Identifying the Goal, User model and Conditions of Recommender Systems for Formal and Informal Learning. Journal of Digital Information. Drachsler, H., Hummel, H., van den Berg, B., Eshuis, J., Berlanga,A., Nadolski, R.,Waterink,W., Boers, N., & Koper, R. (accepted). Effects of the ISIS Recommender System for navigation support in self-organised Learning Networks. Journal of Educational Technology and Society. Drachsler, H., Dries, E.,Arts,T., Rutledge, L.,Van Rosmalen, P., Hummel, H. G. K., & Koper, R. (submitted). ReMashed – Recommendations for Mash-Up Personal Learning Environments. 4th European Conference on Technology Enhanced Learning, EC-TEL 2009. Learning in the Synergy of Multiple Disciplines, September, 29, 2009, Nice, Italy Iyer, B., & Davenport,T. H. (2008). Reverse engineering Google's innovation machine. Harvard Business Review. Kalz, M.,Van Bruggen, J., Giesbers, B., & Koper, R. (2007). Prior Learning Assessment with Latent Semantic Analysis. In F.Wild, M. Kalz, J.Van Bruggen & R. Koper (Eds.). Proceedings of the First European Workshop on Latent Semantic Analysis in Technology Enhanced Learning (pp. 24-25). Heerlen,The Netherlands: Open University of the Netherlands. Gahn, C., Specht, M., & Koper, R. (2007). Smart Indicators on Learning Interactions. In E. Duval, R. Klamma, & M.Wolpers (Eds), Creating New Learning Experiences on a Global Scale: LNCS 4753. Second European Conference on Technology Enhanced Learning, EC-TEL 2007 (pp. 56-70). Berlin, Heidelberg: Springer.