DescriptionIn the last few years, the amount of data has exploded that is published and made publicly available on the web, like governmental data, Web2.0 data from Blogs, Twitter, Flickr or YouTube, and data from various sensors like GPS coordinates from mobile devices. Nowadays, data driven companies like Google, Yahoo, Facebook, Amazon, or Bit.ly are growing exponentially. This new data economy empowers companies to offer an increasing amount of data products without any costs for their users (e.g., Google street view, bit.ly customized URLs, Yahoo Pipes). The data products acquire their economic value from the data itself, and create even more data by attracting users to upload and connect their own data with the data products (Anderson, 2009). This exponentially growing amount of data renewed the interest in information retrieval technologies. Such technologies are used to analyze the data and offer personalized data products to the needs and the context of individual users. Thus, data in combination with information retrieval technologies are the key for the data economy which monetizes its efforts by offering personalized data products to the users. Personalization also promises the educational field improved effectiveness and efficiency of learning processes. It is expected that personalized learning has the potential to reduce delivery costs, create more effective learning environments and experiences, accelerate competence development, and increase collaboration between learners. This matters to initial, school-based learning but even more so to post-initial, lifelong and workplace learning.The data economy also affects the learning landscape that developed with the rise of e-learning environments to a technology enhanced learning reality, where learners can access, read, create, contribute, and share any kind of learning content or find suitable peer learners whenever they want to. The increasing application of interactive learning environments, learning management systems, intelligent tutoring systems, personal learning environments, and the Web2.0 developments allow the collection of large amounts of educational data. Although the TEL domain stores data in their e-learning environments automatically it typically lacks shareable datasets. A good example for that is the research on recommender systems in TEL. A lot of research is conducted but hardly mutually comparable, because no sharable and reusable datasets are publicly available and to the extent that they are, they lack ways to evaluate the performance of TEL recommender systems. The unused educational datasets offer an unexploited potential for the evaluation of learning theories, learning technology, and the development of future learning applications. There is an increasing awareness in the TEL field that the domain needs to create dataset-driven research in order to create more transparent, mutually comparable, trusted and repeatable experiments that lead to evidence-driven knowledge with approved indicators for theories in Technology Enhanced Learning. Furthermore, the lack of educational datasets hinders the development of novel and innovative educational data products that combine different data sources in data mashups like in the e-government domain.
Drachsler, H. (2010, 30 November). Data Sets as Facilitator for new Products and Services for Universities. Invited talk at VOR-ICT Bijeenkomst, Utrecht, The Netherlands: Open University, CELSTEC.
|Period||29 Nov 2010|
|Event title||VOR-ICT Bijeenkomst|