Learning analytics is an emerging and fast growing multidisciplinary field in which data about learners and their contexts are analyzed for understanding and optimizing learning and learning environments. This seminar will discuss two recent and ongoing studies in learning analytics. The first study is on automated analysis of student comments on Wikis of group writing projects. Association rule mining and text categorization are applied to analyze and automatically classify student comments into categories in social interaction, thinking process and thinking development. The second study is to predict student performance based on system logs in Learning Management Systems (LMS). Linear regression with feature selection is used to build prediction models. A framework is proposed to link LMS logs, assessment tasks and learning outcomes. The goal is to design and develop a tool for instructors and students to monitor learning progress in real-time.
<p>Dr. Xiao Hu is an Assistant Professor in the Division of Information and Technology Studies in the Faculty of Education of the University of Hong Kong. Her research interests include learning analytics, applied data/text mining, and information retrieval. She is leading several projects on using learning analytics to improve teaching and learning, and has co-organized Learning Analytics Summer Institute, LASI-Hong Kong in 2013 and 2014. Dr. Hu has experience and background in multiple disciplines. Before joining HKU she was an Assistant Professor in the Morgridge College of Education at the University of Denver. Dr. Hu holds a PhD degree in Library and Information Science and a Master's degree in Computer Science from University of Illinois at Urbana-Champaign, a Master's degree in Electrical Engineering from Beijing University of Posts and Telecommunications, and a Bachelor's degree in Electronics and Information Systems from Wuhan University.<br /><br /></p>