LA-SIG Webinar Recordings
Data Storytelling and Learning Analytics in Physical Spaces, 25 July 2018
Abstract: The aim of this talk was to discuss the potential of a new metaphor for bringing Learning Analytics into blended/hybrid learning spaces that we call Classroom Translucence. A translucent classroom or learning space would be that where activity traces of online and in-the-classroom learning can enhance awareness of teaching and learning practices. Similar to how translucent surfaces are used in architecture, a translucent system would facilitate awareness while ensuring privacy and restricting the use of data for particular situations. This presentation will showcase a series of current and past developments aimed at making teamwork and classroom activity more visible based on this metaphor. We have been rolling out multimodal learning analytics solutions into physical learning spaces to capture traces of activity that can potentially serve as evidence for reflection or for learners and educators to take immediate actions. It is time to connect the best of both worlds in learning analytics: 1) the more developed analytics on computer-mediated student data and 2) emerging physical analytics technologies.
Presenter: Dr Roberto Martinez-Maldonado is a full-time researcher at the Connected Intelligence Centre (CIC) and data visualisation lecturer at the University of Technology, Sydney (UTS). He has a background in Computing Engineering. His areas of research include Human-Computer Interaction (HCI, CSCW), Learning Analytics, Artificial Intelligence (AIED, EDM) and Collaborative Learning (CSCL). In the past years, his research has focused on applying data mining techniques to help understand how people learn and collaborate in co-present environments, empowering people with emerging technologies such as interactive surfaces, combining available technologies for capturing traces of collaboration and helping teachers to orchestrate their classroom through the use of interactive devices and learning analytics innovations. He is program co-chair of the research and industry track program of the International Conference of Artificial Intelligence in Education 2018, held in conjunction with the Festival of Learning in London in June.
Presentation slides courtesy of Dr Martinez-Maldonado: LA-SIG-Martinez-webinar-slides-25-July-2018 (pdf)
Learning analytics and learning design: promoting a conversation among equals, 30 May 2018
Please note that visual content in the recording commences at the 2:20 minute mark.
Abstract: The aim of this webinar was to present a simple Learning Analytics – Learning Design (LA-LD) framework, designed to help teachers to align the use of common types of learning analytics data with the normal rhythms of teaching. The aim in developing the framework was to support reflection in and on action through the familiar cycles of planning, teaching, assessment and review. We used common teaching scenarios to illustrate ways that learning analytics can be used to influence student retention, engagement and achievement, and provide teachers with feedback before, during or after an event. We ran workshops to gain feedback on practical application of the LA-LD framework, and invited participants to develop a plan to use student data in their own teaching context. This entry level professional development strategy was based on two assumptions; that teachers a) are more likely to engage with learning analytics if the potential is presented as a way to support core aspects of their current practice; and b) need to become familiar with learning analytics concepts to represent their interests in design, development and implementation initiatives.
Presenters: Associate Professor Cathy Gunn and Dr Claire Donald, Senior Lecturer, Centre for Learning and Research in Higher Education (CLeaR), The University of Auckland.
Quantitative Ethnography: Human Science in the Age of Big Data, 8 November 2017
Please note that due to a technical glitch, the visual content in this recording does not appear until the 6 minutes mark.
Abstract: In this session, David Williamson Shaffer looked at the transformation of education and the social sciences in the age of Big Data. The tools of Quantitative Ethnography integrate data-mining, discourse analysis, social interactionism, cognition, learning science, statistics, and ethnography into a brand-new human science. We get numbers and meaning both, and they do not fight each other; rather they produce new ideas and innovative ways of thinking about data and data analysis. Those interested in teaching, learning, meaning-making, culture, social interaction, and human development will find here the first shot in a research methods revolution.
Presenter: David Williamson Shaffer is the Vilas Distinguished Professor of Learning Sciences at the University of Wisconsin-Madison, the Obel Foundation Professor of Learning Analytics at the Aalborg University in Copenhagen, and a Data Philosopher at the Wisconsin Center for Education Research. He began his career as a classroom teacher and teacher-trainer in mathematics, history, science, and English as a second language, in the US and with the US Peace Corps in Nepal. Professor Shaffer’s MS and Ph.D. are from the Media Laboratory at the Massachusetts Institute of Technology. He was a 2003-2005 National Academy of Education Spencer Fellow and a 2008-2009 European Union Marie Curie Fellow. He is the author of How Computer Games Help Children Learn (New York: Palsgrave MacMIllan, 2006) and Quantitative Ethnography (Madison, WI: Cathcart Press, 2017).
Presentation slides courtesy of Prof. Shaffer: Prof-Shaffer-LA-SIG-webinar-slides-8-Nov-2017-1.pdf
Video 1 referenced in the presentation: http://youtube.com/watch?v=zyfJAtL93OU
Video 2 referenced in the presentation: http://youtube.com/watch?v=RI8b3x85MVE
A Review of Five Years of Research & Implementation aligning Learning Design with Learning Analytics at the Open University (UK), 20 September 2017
Abstract: The Open University UK has been one of few institutions that have explicitly and systematically captured the designs for learning at a large scale. By applying advanced analytical techniques on large and fine-grained datasets, we have been unpacking the complexity of instructional practices, as well as providing empirical evidence of how learning designs influence student behaviour, satisfaction, and performance. This seminar will discuss the implementation of learning design at the OU in the last 5 years, and reviews empirical evidence from several studies that have linked learning design with learning analytics. Recommendations are put forward to support future adoptions of the learning design approach, and potential research trajectories.
Presenter: Bart Rienties is Professor of Learning Analytics at the Institute of Educational Technology at the Open University UK. He is programme director Learning Analytics within IET and head of Data Wranglers, whereby he leads of group of learning analytics academics who conduct evidence-based research and sense making of Big Data at the OU. As educational psychologist, he conducts multi-disciplinary research on work-based and collaborative learning environments and focuses on the role of social interaction in learning, which is published in leading academic journals and books. His primary research interests are focussed on Learning Analytics, Computer-Supported Collaborative Learning, and the role of motivation in learning. Furthermore, Bart is interested in broader internationalisation aspects of higher education. He has successfully led a range of institutional/national/European projects and received a range of awards for his educational innovation projects.
Presentation slides courtesy of Prof Rienties: Prof B Rienties LA-SIG webinar slides 20 Sept 2017 (pdf)
Data, analytics and learning: interdisciplinary approaches to the generation of actionable knowledge, 9 August 2017
Abstract: Much of Dr Thompson’s research has focused on understanding the complexity of learning situations so that instructors can provide more targeted support to learners. In recent years, this has been referred to as the generation of actionable knowledge, or knowledge that can be used to inform policy and practice. The collection, analysis, and translation of this knowledge into practice are distinct processes, with different tools and expertise required. Multimodal data is necessary to understand complex learning environments, some of which may be generated from ‘big’ learning data, but not all. As we develop additional ways to capture multimodal data, we also need to move towards understanding how to interpret and connect multiple data types, and identify processes and tools to inform this practice. Each data type comes with its own methodological and theoretical assumptions.
In this webinar, Kate talked about the application of an interdisciplinary approach to the generation of actionable knowledge for learning, teaching and research. Interdisciplinary research connects experts from multiple disciplines, to jointly address a question that cannot be entirely answered by a single perspective. Building on research from other fields facing similar challenges, the key steps in interdisciplinary research are to: identify an appropriate research question; develop a shared vocabulary; co-create boundary negotiating objects; visualize and combine data; and produce a new model of understanding. Kate also discussed the challenges and potential of connecting the interpretations of researchers, designers and instructors; using multiple types of data; and multiple theoretical and methodological approaches.
Presenter: Dr Kate Thompson is a Senior Lecturer, Educational Technology, School of Education and Professional Studies at Griffith University. The underlying focus of Dr Thompson’s research is learning sciences, specifically collaborative learning and discovering patterns of learner interaction that could be used by an instructor to indicate progress through a task. Her research in this area influences how educators design for the use of a range of digital technologies as the tool around which collaboration occurs in increasingly complex face-to-face and online collaborative environments. Kate’s research has been applied in collaborative learning and learning situations that include school students (primary and secondary), undergraduate and postgraduate students. A recent focus has been in interdisciplinary collaboration with two core groups: environmental science graduate students (USA), and STEAM (Australia). The impact of this research is widespread in the USA, through a National Science Foundation grant, the team is implementing the research-informed design of collaborative, interdisciplinary problem solving in five institutions, and another five to be added in 2017. In Australia, Dr Thompson leads teams working networks of schools looking at school change mediated by STEAM and Digital Technologies in Brisbane and Canberra.
In 2016 Dr Thompson received funding to lead the Creative Practice Lab (CPL) at Griffith University. Located in a newly constructed learning space in the School of Education and Professional Studies, the CPL combines teacher education and digital technologies, with state-of-the-art video recording and online collaboration systems. The ultimate aim of the research in the CPL is to understand pedagogical practices in contemporary learning spaces, learning analytics informed practice, and online collaboration and design.
Presentation slides courtesy of Dr Thompson: Dr-Kate-Thompson LA-SIG webinar slides 9 August 2017 (pdf)
Responsible Learning Analytics: A Tentative Proposal, 21 June 2017
Abstract: Implied in learning analytics as research focus and field of praxis, is the notion of “responsible learning analytics” – though it is certainly not a dominant theme. An overview of the social imaginary pertaining to learning analytics points to a range of topics, such as the huge potential in the collection, analysis and use of student data and emerging evidence of its use in a range of higher education contexts.
In the noisy scholarly, public and increasingly commercial spheres of claims and counter claims pertaining to a range of applications for learning analytics, there are also voices emphasising that we should not forget that learning analytics is about students and their learning. Often to the frustration of venture capitalist/commercial vendors of learning analytics software and systems, there are also scholars who ask uncomfortable questions such as the scope of student privacy and the need to move towards student-centred learning analytics. The range of ethical considerations in the collection, analysis and use of student data and increasingly, the moral fiduciary obligation arising from our collection and analysis of student data – are often uncomfortable reminders of unchartered fields of scholarly reflection and empirical research.
An etymology of the word ‘responsible’ points not only to the need to be answerable and accountable, but also to being response-able and the obligation to act. In this presentation, I propose that an answerable but also a response-able approach to learning analytics cut across the whole spectrum of the collection, analysis and use of student data. The fiduciary duty of higher education and the asymmetrical power relationships between higher education and students serve as basis for my exploration of accountability and response-ability in learning analytics. I will engage with a selection of issues in the collection, analysis and use of student data such as our beliefs regarding data and evidence; data quality, scope, and governance; student participation and the ethics of (not) knowing before concluding with a tentative proposal.
Presenter: Paul Prinsloo is a Research Professor in Open and Distance Learning (ODL) in the College of Economic and Management Sciences, University of South Africa (Unisa). His academic background includes fields as diverse as theology, art history, business management, online learning, and religious studies. Paul is an established researcher and has published numerous articles in the fields of teaching and learning, student success in distance education contexts, learning analytics, and curriculum development. His current research focuses on the collection, analysis and use of student data in learning analytics, graduate supervision and digital identity.
Presentation slides courtesy of Paul Prinsloo: Paul Prinsloo LA-SIG webinar slides 21 June 2017 (pdf)