Abstract

In social networks,social foci refer to physical or virtual entities around which socialindividuals organize joint activities, for example, places and products inphysical form or opinions and services in virtual form. Forecasting whichsocial foci will diffuse to more social individuals is important to businessand public functions such as planning, marketing, and operations. Consideringdiffusive social adoptions, prior studies on user adoption behavior in socialnetwork contexts has focused on single-item adoption in homogeneous socialnetworks. We advance this body of research by modeling the scenarios ofmulti-item adoption and learning for the relative spread of concurrent socialdiffusions of social foci in online social networking platforms. To bespecific, we distinguish two types of social nodes, social foci and socialactors by proposing a two-mode social network model. Based on social networktheories, we identify and operationalize factors that drive social adoption,within the two-mode social network. We also capture the interdependencesbetween social actors and social foci using a bilateral recursive process,namely, mutual reinforcement process that converges to an analytical form.Given the proposed model and the converged process, we thereby develop agradient learning method based on mutual reinforcement process (GLMR) thattargets on optimal parameter configuration for pairwise ranking of socialdiffusion spreads. Further, we show analytical properties of our method such asguaranteed convergence and convergence rate. In the evaluation, we benchmarkagainst prevalent methods and show the superior performance of our method usingthree real-world data sets that cover adoptions about both physical and virtualentities from online social networking platforms. 

Time

7月26日（星期五）14:00—16:00

Speaker

Zhepeng (Lionel) Li is an Associate Professor in theArea of Operations Management and Information Systems at the Schulich School ofBusiness, York University, Toronto, Canada. He has received his Ph.D. inInformation Systems with a minor in computer science from the University ofUtah, USA. His research broadly falls in computational data science for deepbusiness analytics. Specific research interests concentrate on applying machinelearning approaches to address business problems including social recommendations,targeted marketing, network analytics, FinTech, and PropTech. His works arepublished by top-tier research journals, such as Management Science andInformation Systems Research. The published researches are also covered bymedia, such as MIT technology review. His research activities are supported byNatural Sciences and Engineering Research Council of Canada (NSERC) discoverygrants and industrial sponsors.

Venue

信息管理与工程学院308室

上海财经大学（第三教学楼西侧）

上海市杨浦区武东路100号