[5-12]軟件所青年聯合會第39期活動---Computational Lens on Large-Scale Social Networks
文章來源： | 發布時間：2016-05-10 | 【打印】 【關閉】
報告摘要:
The interactions between individuals form the structural backbone of human societies, which manifest as networks. In a network sense, individuals matter in the ways in which their connections activate the emergence of new phenomena at larger, societal levels. In this talk, I will introduce how we leverage newly available planetary-scale user base to unveil the diverse ways that different people are embedded in various social systems, and provide computational models of individual behavior and collective phenomena. First, from a nationwide mobile communication networks, we unveil the significant social strategies that are used by people to satisfy their social needs across the lifespan. Second, using a collection of 116 large-scale networks, we define the structural diversity of common neighborhood and further leverage this definition to develop a unique network signature, with which we discover several distinct network superfamilies not discoverable by conventional methods. Finally, we apply computational models to address data mining tasks in large-scale social networks, including user demographic inference, link recommendation, and social impact prediction in social networks. To this end, modeling social interactions in digital environments offers the potential to understand the fundamental principles that drive our social decisions and activities—from individuals, to cultures, to societies—and, in this way, to help us better understand ourselves and each other.
報告人簡介:
Yuxiao Dong is currently a Ph.D. candidate in Computer Science and Engineering and the Interdisciplinary Center for Network Science and Applications (iCeNSA), University of Notre Dame, U.S. His research focuses on social networks, data mining, and computational social science, with an emphasis on applying computational models to addressing problems in large social systems, such as mobile communication, online social media, and academic collaboration. His research has been published in data science conferences (e.g., SIGKDD, WSDM, ICDM, ECML/PKDD, etc.) and interdisciplinary journals (e.g., Scientific Reports and PLoS ONE), and also won two best paper awards/nominations.
