科学研究

Ping Luo is currently an Associate Professor at Institute of Computing Technology, Chinese Academy of Sciences. Before joining ICT, he worked as Senior Research Scientist at the Hewlett-Packard Labs. His general area of research is knowledge discovery and machine learning.  Recently, Dr. Luo is interested in Computational Behavioral Science using Internet as the natural laboratory.

He has published 30+ papers in some prestigious refereed journals and conference proceedings, such as IEEE Transactions on Information Theory, IEEE Transactions on Knowledge and Data Engineering, Journal of Parallel and Distributed Computing, ACM SIGKDD, ACM CIKM, IJCAI. He is the recipient of the Doctoral Dissertation Award, China Computer Federation (2009), the ACM CIKM Best Student Paper Award (2012).

 Nowadays, people often spend lots of time on hedonic content systems, like browsing Facebook, Weibo, Wechat, everyday news, pictures etc., via mobile apps. When you are scrolling through Facebook, have you ever found you just cannot stop it even there is nothing worth to see? When you are watching online videos, have you ever found sometimes you turn off it just after a few minutes, but sometimes you become a couch potato? This phenomenon actually happens when we are playing computer games, do shopping online, and also in plenty of similar Hedonic Content Systems (HCS).

In this talk, we will study the behavioral and psychological nature behind the user browsing process in these hedonic content systems. Specifically, we focus on the selection on whether to continue browsing or leave. This selection in HCS is completely free and unconscious, and basically influenced by some behavioral and psychological factors. Based on the large scale of user logs from a wallpaper mobile app, we find two interesting observations, named Attention Valley and Stimulus Mountain. Also, we propose a Joy-Satiety-Compete model to explain the observations, and discuss its relationship with some important behavioral concepts such as attention blink, status quo bias, and stimulus vs. sensations. Finally, we show how the app operators could make more profits if they could understand these behavioral characteristics of user browsing.