Programme of FLAIEC 2022

Validity of measurement: We can’t ignore it in learning analytics

Abstract: The emergence of learning analytics afforded for the analysis of digital traces of user interaction with technology. This analysis offers many opportunities to advance understanding and enhance learning and the environments in which learning occurs. Existing research has shown how learning analytics can provide contributions to different areas of education such as prediction of student success, uncovering learning strategies, understanding affective states, and unpacking the role social networks in learning. While these results have shown much promise, one critical challenge remains unclear – how learning analytics can offer valid measurements of learning processes and outcomes. This talk will explore opportunities and challenges for advancement of validity of measurement in learning analytics. The talk will build on examples from research on self-regulated learning, teamwork, and language learning.

Biography: He is Professor of Learning Analytics of the Faculty of Information Technology and Director of the Centre for Learning Analytics at Monash University. Previously, he was a Professor and the Sir Tim O’Shea Chair in Learning Analytics and Informatics in the Moray House School of Education and the School of Informatics at the University of Edinburgh (2015-2018) and a Professor and Canada Research Chair in Semantic and Learning Technologies at Athabasca University (2007-2015). He served as the president (2015-2017) of the Society for Learning Analytics Research (SoLAR) and has held several honorary appointments in Asia, Australia, Europe, and North America. His research is focused on computational methods that advance understanding of self-regulated and collaborative learning. He has led and studied systemic adoption of learning analytics in higher education.

Advancing socially shared regulation with AI

Abstract: There is global consensus that a new set of uniquely human skills and competencies will be necessary to succeed in a rapidly changing world, especially those that machines cannot match or replicate. These skills and competencies are central to research on regulation of learning in collaborative contexts, namely socially shared regulation of learning (SSRL). In this talk I will introduce the progress of that research and what are the novel opportunities advanced learning technologies and related data can offer for SSRL. I stress that systematic understanding of human learning process is needed to leverage full potential of AI to help learners and AI to work and learn together.

Biography: She is a professor in the field of learning and educational technology and a head of the Learning and Educational Technology Research Unit (LET). She is the co-chief editor of International Journal of Computer Supported Collaborative Learning (iCSCL) and invited member of the expert group of the OECD’s PISA 2025 ‘Learning in the Digital World’. She has published more than 200 peer-reviewed journal articles. Järvelä and her research group is internationally well known from theoretical advancement of social aspects self-regulated learning (SSRL). Her interdisciplinary research work has strong contribution to the methodological development of process-oriented research methods in the field of learning and collaboration and recently applying of multimodal methods in self-regulated learning research.

Dirk Ifenthaler

Professor, University of Mannheim, Germany

In search for validity of learning analytics indicators

Abstract: Recent developments in learning analytics, which are a socio-technical data mining and analytic practice in educational contexts, show promise in supporting learning processes and enhancing study success in higher education, through the collection and analysis of data from learners, learning processes, and learning environments in order to provide meaningful feedback and scaffolds when needed. However, an analysis of more than 35,000 publications shows that rigorous, large-scale evidence on the effectiveness of indicators for learning analytics in supporting learning processes and study success is still lacking. This presentation will review the promises and opportunities of learning analytics and tackle challenges of implementing indicators into productive higher education eco-systems.

Biography: He is Professor and Chair of Learning, Design and Technology at University of Mannheim and UNESCO Deputy Chair of Data Science in Higher Education Learning and Teaching at Curtin University, Australia. His previous roles include Professor and Director, Centre for Research in Digital Learning at Deakin University, Australia, Manager of Applied Research and Learning Analytics at Open Universities, Australia, and Professor for Applied Teaching and Learning Research at the University of Potsdam, Germany. His research focuses on the intersection of cognitive psychology, educational technology, data analytics, and organizational learning. His research outcomes include journal articles, co-authored books, book series, book chapters, and international conference papers. Furthermore, he has grant funding in Australia, Germany, and USA.

Possibilities of learning analytics pedagogy to support student learning – multiple case studies

Abstract: This keynote presents perspectives and findings of the OAHOT-research project, which aimed to draw together and better understand the possibilities to support higher education and primary education students’ self-regulated learning and learning processes through the pedagogical use of Learning Analytics (LA). In the primary education students participated in two phenomenon-based study modules, which was designed to support self-regulated learning and reflection skills in a blended learning environment and utilized learning analytics and their visualizations. In the higher education context four courses were built to support online or blended learning with LA tools and visualizations. Students’ experiences were mainly positive, but various profiles of using learning environments and LA data as part of it were recognized. Behavioral and emotional experiences seemed to be related, and careful utilization of LA data and tools to support learning may activate even students with a more negative experiences towards the contents of the modules. Also, it seems that students, who used LA data and visualizations more actively, had more favorable experience of them. We also had a larger institution level LA data of vocational education, according to which it seems that teachers’ and institutions would need more clearly defined processes for data input to assure the quality of institutional level data. This would require more accurate understanding among teachers of the possible uses of data to support student learning. This keynote will draw together the key insight acquired of the pedagogy of/for learning analytics to support students’ learning.

Biography: Laura Hirsto is a Professor of Educational Science in the University of Eastern Finland, Department of Applied Educational Science and Teacher Education. Hirsto is supervising various research and development projects related to academic and educational development, student learning and teacher learning and pedagogical perspectives on learning analytics in various contexts. Her research interests are in higher education students’ and teacher students’ as well as primary level pupils’ learning and motivational processes, and in variations of effective teaching and learning environments. Professor Laura Hirsto is the Project Leader (PI) of the Business Finland funded OAHOT research project (https://sites.uef.fi/oahot/). Her keynote will be prepared in collaboration of the OAHOT research project team, and key findings of the project will be presented.