Keynote: Dimensions on Texts
With unlimited expansion of texts in the cyberspace, information service based on text understanding becomes more and more desirable. Text summarization is an important technology that helps people to know a big set of texts by reading a small piece of text. Traditional automatic summarization methods process texts empirically while neglecting fundamental characteristics and principles in language use and understanding. This talk summarizes previous research methods by using a four-dimensional classification space, criticizes previous methods, introduces fundamental characteristics and principles, and proposes a multi-dimensional summarization methodology including principles, strategies, rules, research methods, system framework, and criteria of evaluation.
Prof. Zhuge is the pioneer of the Knowledge Grid research and Cyber-Physical Society research. The Cyber-Physical Society represents his ideal of the future human-machine-nature symbiosis environment. He defined the notion and opened scientific issues for the first time. He has proposed a set of principles and methods, and carried out multi-disciplinary research toward the ideal.
He is the author of over 130 papers appeared mainly in leading international journals and conferences such as Artificial Intelligence, Communications of the ACM, IEEE Computer, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Parallel and Distributed Systems, ACM Transactions on Internet Technology, Journal of the American Society for Information Science and Technology and VLDB, IJCAI and CIKM. He also serves as a review expert of national award of China and several national foundations such as NSF of Austria, NSF of China, SFI of Ireland, NSF of Korea, and NSF of USA.
Keynote: From Sentiment to Emotion Analysis in Social Networks
We first study the problem of user-level sentiment analysis. Employing Twitter as a source for our experimental data, we show that information about social relationships (e.g., retweeting and following) can be used to improve user-level sentiment analysis. We further explore the fundamental factors that underlying users’ sentiments. In particular, we focus on quantitative study of users’ emotional states in social networks. Emotion stimulates the mind 3000 times quicker than rational thought. Such emotion invokes either a positive or a negative response and physical expressions. We have developed a “happy” system and deployed it in Tsinghua University. Based on the collected data, we statistically study the dynamics of individual’s emotions and discover several interesting as well as important patterns.
Jie Tang is an associate professor at the Department of Computer Science and Technology, Tsinghua University. He was honored with the CCF Young Scientist Award, NSFC Excellent Young Scholar, IBM Innovation Faculty Award, and the New Star of Beijing Science & Technology. His research interests include social network analysis, data mining, and machine learning. He has been visiting at Cornell University, HKUST, and CUHK.
He has published more than 100 journal/conference papers (in major international journals and conferences including: KDD, IJCAI, WWW, SIGMOD, ACL, Machine Learning Journal, TKDD, and TKDE) and held 10 patents. He also served as Workshop Co-Chair of SIGKDD’13, Local Chair of SIGKDD’12, Publication Co-Chair of SIGKDD’11, Program Co-Chairs of ADMA’11 and SocInfo’12, and also serves as the PC member of more than 50 international conferences. He is now leading the project Arnetminer.org for academic social network analysis and mining.