Authors: Bryan Runck*, University of Minnesota
Topics: Geographic Information Science and Systems, Coupled Human and Natural Systems, Quantitative Methods
Keywords: agent-based modeling, human decision-making, simulation, ABM, GIS, qualitative GIS
Session Type: Poster
Start / End Time: 1:20 PM / 3:00 PM
Room: Napoleon Foyer/Common St. Corridor, Sheraton, 3rd Floor
Presentation File: No File Uploaded
Generating replicable and empirically valid models of human decision-making is crucial for the scientific accuracy and reproducibility of agent-based models. A two-fold challenge in developing these models of decision-making is a lack of high resolution and high quality behavioral data and the need for more transparent means of translating these data into models. A common and largely successful approach to modeling decision-making is the heuristics and biases approach. In this approach, the researcher hand-crafts agent decision heuristics from qualitative field interviews. This empirically-based, qualitative approach successfully incorporates contextual decision making, heterogeneous preferences, and decision strategies. However, it is labor intensive, often leads to models that are hard share and replicate, and typically offers a static representation of agents, thereby limiting the scale and scope over which such methods can be usefully applied. A potential solution to these problems is provided by new approaches in natural language processing (NLP), which can use textual sources ranging from field interview transcripts to unstructured data from the web to capture and represent human cognition. In this paper, I integrate NLP techniques with Construal Level Theory to create agents that construct mental models through interaction with other agents and the environment. I validate this model of agent decision-making through controlled experiments deployed on the Amazon Mechanical Turk. The model effectively represents human likelihood assessments and decision making, and offers a new way to model agent cognitive processes for a broad array of human-environmental systems.