Keynote 1 and Keynote 3: http://optnetsci.cise.ufl.edu/cocoon16/keynote.html
Ee-Peng Lim Multimodal Sensemaking using Social Media Data
Professor of Information Systems
Director, Living Analytics Research Centre
School of Information Systems
Singapore Management University
80 Stamford Road
Ee-Peng Lim is a professor at the School of Information Systems of Singapore Management University (SMU). His research interests include social network and web mining, information integration, and digital libraries. He is the Co-Director of the Living Analytics Research Center (LARC) jointly established by SMU and Carnegie Mellon University. He is also the Associate Editor of several journals including ACM Transactions on Information Systems (TOIS), ACM Transactions on the Web (TWeb), IEEE Transactions on Knowledge and Data Engineering (TKDE), Information Processing and Management (IPM), Social Network Analysis and Mining, Journal of Web Engineering (JWE), and IEEE Intelligent Systems. He serves on the Steering Committee of the International Conference on Asian Digital Libraries (ICADL), Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD), and International Conference on Social Informatics (Socinfo).
As social media becomes an integral part of daily lives, it captures many interesting user-generated content and behaviour data that can be sensed and analysed. While social media companies use the insights learnt from such data to improve their user interface and experience, there are many other interesting insights that help us improve urban environment and public services. Social media data also offers a cheap and scalable approach to perform sensemaking on the urban environment. In this talk, we will showcase a few ongoing research projects in the Living Analytics Research Centre (LARC) which focus on multimodal sensemaking using social media data. The talk will share some new machine learning methods and systems to profile users, locations, and public transport services. The reasonably good accuracy of these methods also allow them to be deployed in urban application solutions.