Simulating Online Social Response: A Stimulus/Response Perspective

The paper describes a methodology for simulating online social media activities that occur in response to external events. A large number of social media simulators model information diffusion on online social networks. However, information cascades do not originate in vacuum. Rather, they often originate as a reaction to events external to the online medium. Thus, to predict activity on the social medium, one must investigate the relation between external stimuli and online social responses. The paper presents a simulation pipeline that features stimulus/response models describing how social systems react to external events of relevance to them. Two case studies are presented to test the fidelity of different models. One investigates online responses to events in the Venezuela election crisis. The other investigates online responses to developments of the China Pakistan Economic Corridor (CPEC). These case studies indicate that simple macroscopic stimulus/response models can accurately predict aggregate online trends.