Modeling Human Behavior on Social Media in Response to Significant Events

Social media provides abundant, naturally occurring data on communications among people that can reveal their behavior. Recent technological advancements have made possible the rapid processing of social media data with the potential to learn more about human behavior. In order to do so, however, there is a need for a comprehensive and integrative theoretical model of human behavior as expressed in social media. In addition, such a model should provide specific avenues for staging behavioral interventions. The objective of this paper is to address this deficiency in the context of behaviors that occur in response to significant events. Relevant theories of human behavior are presented as well as a methodology, utilizing natural language processing and social network analysis, for measuring elements of human behavior. The methodology provides numerical measures for each element, which serve as input data for the multivariate statistical model used to answer research questions in a case study of human behavior in response to a natural disaster. For this case study, three behaviors associated with the warning response process were modeled: 1) obtain and propagate the warning; 2) seek additional information/confirmation; and 3) take the prescribed action. Emergency managers can use the findings of the research to help ensure that people obtain critical information and take prescribed actions, such as evacuating a flood zone. Once the dynamics of human behavior as expressed in social media are understood, models can be built to predict human behaviors well in advance of their recommended or anticipated occurrence.