Abstract
Knowing and being aware of students’ learning styles and therefore how individual students prefer to learn has many advantages for educators and students. For example, such knowledge increases educators’ and students’ understanding about students’ learning processes, allows educators to provide better support for their students, enables students to understand their strengths and weaknesses when it comes to learning, and therefore has high potential to enhance learning and teaching in general. While there exist questionnaires to get information about students’ learning styles, such questionnaires have several disadvantages. Given the increasing use of educational technology (e.g., learning management systems such as Moodle), research has been conducted on automatically extracting students’ learning styles from how students use such educational technology. This talk will focus on how to automatically identify learning styles of students in the area of computer science based on their behaviour in learning management systems. First, the talk will present research about the relationships between students’ behaviour in learning management systems and their learning preferences and learning styles. Subsequently, a rule-based approach will be introduced that automatically identifies learning styles of students in the area of computer science, and its successful evaluation with 75 students will be presented. The rule-based approach has been implemented as a stand-alone tool, called DeLeS, which will be shown in the talk, together with how learning styles and related recommendations are visualized to students and educators. In addition, research about improving the accuracy of the rule-based identification approach through the use of computational intelligence algorithms will be introduced.

Bio
Dr Sabine Graf is an Associate Professor at Athabasca University, School of Computing and Information Systems, in Canada. In 2007, Dr Graf received a PhD from Vienna University of Technology, Austria. Afterwards, she worked for one year as postdoctoral researcher at National Central University, Graduate Institute of Learning and Instruction, in Taiwan. Subsequently, she joined Athabasca University, first as a postdoctoral fellow through an Erwin Schrödinger Fellowship funded by the Austrian Science Fund (FWF), then as Assistant Professor and currently she holds a tenured Associate Professor position.
Dr Graf’s research is at the intersection of educational technology, personalization and learning analytics, with the focus on enhancing computer science education. As such, her research aims at designing, developing and evaluating technical concepts/algorithms, didactical approaches, and technologies to support teaching and learning of computer science topics. She has published more than 120 peer-reviewed journal papers, book chapters, and conference papers which have been cited over 3,000 times and four conference papers were awarded with a best paper award. Dr Graf is Executive Board Member of the IEEE Technical Committee on Learning Technologies, Editor of the Bulletin of the IEEE Technical Committee on Learning Technology, and Associate Editor of the International Journal of Interaction Design and Architectures. Furthermore, Dr Graf is editorial board member of five international journals and has been workshop chair and organizer of 16 international workshops, doctoral consortium chair at six international conferences, and guest editor of five special issues. She has been invited to given keynote/invited talks at universities, companies and conferences in Austria, Canada, Chile, China, Colombia, New Zealand, Spain, Taiwan, and UK. Furthermore, Dr Graf has been reviewer for research funding applications for programs in Austria, Canada, Chile, Croatia, France, Israel, Netherlands, Singapore and United Arab Emirates.