题目：Towards deep learning analytics based on cognitive modeling
报告人：徐贯东 悉尼科技大学副教授
地点：学院101会议室
时间：2016年12月22日（星期四）上午10：00
学术报告简介:
The wide use of computer aided educational settings boosts the research in educational data mining and learning analytics. In this talk we are going to report our recent studies on deep learning analytics based on cognitive modelling. We propose a fuzzy cognitive diagnosis model to mine the specific skill proficiency of the examinees based on their performance of objective and subjective problem. We design a Bayesian network based method to detect “slip & guess” from examinees’ responses with the obtained skill proficiency. We study the gaming-the-system behaviour in intelligent tutoring systems and develop a framework that models student learning by combining the knowledge and gaming factor based on multiple-attempt responses.
Bio: Dr Guandong Xu is an Associate Professor (Reader) at the School of Software and the Advanced Analytics Institute, University of Technology Sydney. His research interests cover Data Mining, Web Analytics, Text Mining, Recommender Systems, Social Network Analysis and Social Media Mining. His research has gained grant funding from Australian and Chinese governments, e.g., ARC and NSFC grants, and projects from industries. In last ten years, he has had over 100+ publications including TOIS, TNNLS, TIFS, TSC, Inf Sci, IJCAI, AAAI, WWW, ICDE, ICDM, and CIKM. He is the Assistant EiC of WWW Journal. He received Australian BigInsight Data Analytics Award in December 2016 due to his significant impact on Best Customer Value.