【学术报告】社交网络上的群体行为
报告题目:社交网络上的群体行为
报告人:冷妍,德克萨斯大学奥斯汀分校McCombs商学院助理教授
邀请人:夏昊翔,经济管理学院、大数据与智能决策研究中心
报告内容摘要
Social networksare ubiquitous and shape individual behaviors; yet, behavioral data overnetworks are complex and stretch the limit of conventional analysis and models.In this talk, Dr. Leng presents two complementary projects that extend existingprediction and inference methods over social networks. First, she investigatedhow social network influences behavior. Using two large-scale mobile phonedata, she found out that social influence on non-routine behaviors spread up tomore than three degrees of separation with a decay pattern. To explain such aphenomenon, she built a Bayesian model in which individuals locally aggregateinformation and dynamically make adoption decisions. Second, Dr. Lengintroduces a machine learning framework to infer the unobserved networkstructures from decisions. Specifically, the modeled individual decisions usingthe linear-quadratic game and inverted the sparse network structures from theequilibrium actions. Together, this line of work contributed to theunderstanding of human behavior over networks via computational methods, whichare important for managing large-scale behavioral change.
报告人简介
冷妍,德克萨斯大学奥斯汀分校McCombs商学院助理教授,2020年5月在MIT媒体实验室获得博士学位,拥有麻省理工学院的计算机科学和运输工程双硕士学位。主要关注社会科学问题,致力于机器学习,网络理论和因果推理的交叉研究。其研究使用大规模行为数据探究社交网络上的人类群体行为,采用计算技术解决社会和组织领域的科学问题。时间:2020年8月3日9:00-10:30
腾讯会议:900 130 559
大数据与智能决策研究中心介绍
为推动我校多学科交叉的学科前沿创新、提升服务国家和区域经济社会发展重大需求的能力、促进跨学科复合型人才培养、培育新的学科生长点,由王众托院士发起,于2019年1月2日成立大连理工大学大数据与智能决策研究中心,由经济管理学院负责管理,开展大数据与智能决策交叉学科重大项目研究。
往期回顾