Prof. Bary Smyth
School of Computer Science and Informatics, University College Dublin, Ireland [homepage],
Prof. Barry Smyth is the Digital Chair of Computer Science in the of Computer Science and Informatics at University College Dublin. He is also the Director of CLARITY, the Centre for Sensor Web Technologies, a Science Foundation Ireland funded research centre that employees 100+ researchers. Barry’s research interests include artificial intelligence and recommender systems. He has published over 350 scientific papers in leading journals and conferences and received numerous awards for his research. Barry is also an experienced entrepreneur, having co-founded ChangingWorlds (acquired by Amdocs Inc, 2008) and a new social search company, HeyStaks, which recently secured €1m in venture capital funding.
Social Information Discovery
The world of web search is usually viewed as a solitary place. Although millions of searchers use services like Google and Yahoo everyday, their individual searches take place in isolation, leaving each searcher to fend for themselves when it comes to finding the right information at the right time. Recently, researchers have begun to question the solitary nature of web search, proposing a more collaborative search model in which groups or users can cooperate to search more effectively.
For example, students will often collaborate as part of class projects, bringing together relevant information that they have found during the course of their individual searches. Indeed, despite the absence of explicit collaboration features from mainstream search engines, there is clear evidence that users implicitly engage in many different forms of collaboration as they search, although, these collaboration “work-arounds” are far from ideal. Naturally, this has motivated researchers to consider how future web search engines might better support different types of collaboration to take advantage of this latent need; for example, how might students collaborate as they search rather than defer the sharing of information as a post-search activity.
In this talk we focus on some of the ways in which web search may become a more social and collaborative experience. This will include lessons learned from both the theory and practice of a more collaborative approach to web search and we will describe recent attempts to bring collaboration support to mainstream search engines. We will consider a number of educational use-cases during the course of this talk to describe how instructors and learners can take full advantage of this more social perspective on web search.
Erik-Jan van der Linden, Ph.D.
CEO/Owner, MagnaView B.V., the Netherlands [company homepage]
Erik-Jan van der Linden (firstname.lastname@example.org) obtained a Ph.D. in computational linguistics. He worked at Max Planck Nijmegen and the universities of Nijmegen, Tilburg and Amsterdam (1985-1996). He actively published, and gave (invited) presentations on his work in over 10 countries (amongst others in Sydney, Helsinki, Munich, Edinburgh, Stanford, Moscow, Budapest). Van der Linden was self-employed IT-consultant (1996-2007) before founding MagnaView (2003) in cooperation with the Eindhoven University of Technology. MagnaView was selected as Nominee for the European ICT prize 2007, and Nominee for the ICTregie Award 2009. Van der Linden is frequently invited as speaker on the topic of the creation of value from data in sectors where MagnaView is active, such as education, medical diagnostics and the legal sector.
On exploration and mining of data in educational practice
Educational institutions are confronted with increasing pressure from authorities and governments to justify their spending of public means. This, in turn, has led to increased internal use of the huge amounts of data in information systems on results, careers, absence, etc. Experience with a data analysis product that is actively used in 20+ schools (secondary education) indicates that visual presentation and user interaction are crucial to have analyses of large datasets lead to real improvement. Intricate and finely-tuned interaction between methods from the field of data mining and these interactive techniques may further aid schools.
Dr. John Stamper
Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, PA, USA [homepage]
Dr. John Stamper is DataShop Technical Director at the Pittsburgh Science of Learning Center and a member of the research faculty at the Human-Computer Interaction Institute at Carnegie Mellon University. His research centers on using student log data to improve intelligent tutoring systems. The PSLC DataShop has data from hundreds of 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. Currently over 200 datasets are stored including over 42 million student actions. 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. In 2010 John Stamper co-organized Educational Data Mining Challenge at KDD Cup, ACM SIGKDD 2010, the premier international forum for data mining researchers and practitioners from academia, industry, and government. This event was a great success and the lessons learned from it will be shared at EDM 2011.
EDM and the 4th Paradigm of Scientific Discovery – Reflections on the 2010 KDD Cup Competition
Technology advances have made the ability to collect large amounts of data easier than ever before. These massive datasets provide both opportunities and challenges for many fields and education is no different. Understanding how to deal with extreme amounts of student data in the EDM field is a growing problem. The 2010 KDD Cup Competition, titled “Educational Data Mining Challenge”, included data for over 10,000 students. The students completed over 30 million problem steps collected over a year long courses from Carnegie Learning Inc.’s Cognitive Tutors. We believe these are the largest educational dataset at this level of granularity to be released publicly. The competition drew broad interest from the data mining community, but it was also clear that many in the research community could not handle datasets of this size. In this talk, John will discuss the 2010 KDD Cup and the impact of larger and larger amounts of data coming available for educational data mining and how this will drive the direction of educational research in the future.