The 3rd Educational Knowledge Management Workshop

Serge Garlatti is a full professor and head of the computer science department at IMT Atlantique, co-head of a research group on Technology-Enhanced Learning and Cultural Heritage (belonging to IHSEV Team of the Lab-STICC laboratory) and member of ATIEF (Association des Technologies de l’Information pour l’Education et la Formation) and AFIA (Association Française pour l’Intelligence Artificielle), board chairman of ATIEF (from July 2015).
For about 20 years, he worked at the intersection of the fields of Artificial Intelligence (knowledge engineering) and TEL (Technology Enhanced Learning). Its research activities focus on the fields of learning, lifelong learning and cultural heritage for formal and informal learning and the design of new computing environments to support researchers in History of Science and Technology - Digital Humanities. He is interested in the design of learning and cultural mediation environments based on investigative approaches or connectivism, using social media in open environments. From a knowledge engineering point of view, the issues are as follows: knowledge engineering, learning analytics, semantic web and Linked Data, context sensitivity and adaptation, learning analytics, and dynamic generation of dashboards to support stakeholders.

Abstract: In this talk, we explore some knowledge management issues related to a recent approach for life Long Learning providing semantic open learner models and trusted collaborative services. It relies on a project called SEDELA, “SElf-Data for Enhancing Lifelong learning Autonomy”. It gathers researchers from both IT and education science fields. The project aims to enhance learner’s autonomy skills in a lifelong learning perspective as well as develop, experiment and implement an innovative self-data management approach.
Indeed, autonomy is considered as a central asset for lifelong learning. Autonomy in adult education is defined as “the ability to take charge in one’s learning”, meaning specifically “determining the objectives; defining the contents and progressions; selecting methods and techniques to be used; monitoring the procedure of acquisition properly speaking (rhythm, time, place, etc.); evaluating what has been acquired”. Autonomous learners must have the capacity for critical reflection, decision-making, and independent action. However, independence does not mean isolation, as others often constitute resources for autonomous learners. Therefore, supporting students to develop their autonomy’s skills has become a major issue for higher education.
Based on previous research (Nguyen & Ikeda, 2015, the effects of ePortfolio-based learning model on student self-regulated learning), we suggest that implementing a self-data management approach may have a positive effect on the learner’s autonomy skills development. Instead of using an ePortfolio-based learning model, we take advantage of explicit Open Learner Models to develop autonomy and to support self-regulated learning process in personal and professional development. Trusted and long-term capitalization will enable lifelong perspective. Trusted collaborative services will provide the needed socialization for lifelong learning and organizational knowledge creation.
Semantic Open Learner Models will be developed to support autonomy by making informal or incidental learning resources more explicit. This will be achieved by capturing, managing, sharing, etc., personal learning data from various heterogeneous sources with semantic enhancement. Semantic models will enable long term management and trusted collaborative services.
Trusted collaborative services will provide self-development and socially shared knowledge on learning process. Trust will be based on Usage Control. The semantic nature of the models will enable development of new data integration possibilities and services. This will make lifelong learning explicit and visible to foster collaborative activities and knowledge creation in communities, thus empowering learners.

Elsa Cardoso is an Assistant Professor at Instituto Universitário de Lisboa (ISCTE-IUL), in the Information Sciences and Technologies Department of the School of Technology and Architecture. She is the Director of the Master in Integrated Business Intelligence Systems at the same university and the leader of the Business Intelligence Task Force of EUNIS (European University Information Systems organization). She is also a researcher at the Information and Decision Support Systems Group of INESC-ID Lisboa, Portugal. She has a PhD (European Doctorate) in Information Sciences and Technologies from ISCTE-IUL, with a specialization in Business Intelligence.
Her research interests include business intelligence and data warehouse, data visualization, and strategic information systems (balanced scorecard) applied to Higher Education, Healthcare and Digital Humanities.

Abstract: Learning Analytics (LA) is a recent research area, in which Business Intelligence and Analytics techniques are applied to learners and their contexts, with the purpose of acquiring a greater insight about the entire learning process (including outcomes). In this talk, we explore the LA landscape, delving into the definitions, techniques, challenges, and lessons learned. A comprehensive analysis of LA projects across different countries enabled the collection of past and present challenges, as well as lessons learned, which may be useful to new researchers entering this field. A look into the future of LA is also explored, considering current data management challenges that our society faces and how they may impact teaching and learning in Higher Education.
Keywords: Learning Analytics; Techniques; Lessons learned; Challenges