Extended decision field theory with social-learning for long-term decision-making processes in social networks

Modeling and analysis of human behaviors in social networks are essential in fields such as online business, marketing, and finance. However, the establishment of a generalized decision-making framework for human behavior is challenging due to different decision structures among individuals. Thus, we propose a new decision-making framework, Decision Field Theory with Learning (DFT-L), which combines the DFT model and the DeGroot model. We investigated three factors influencing preference evolution: previous experiences, current evaluations, and neighbors’ preferences. The equilibrium status of social networks within this framework is obtained as an explicit formula under the independent and identically distributed (IID) conditions on weight values. This facilitates the identification of limiting expected preference values and covariance matrices. A simulation analysis using simulated and real networks is performed to validate the DFT-L framework and to demonstrate its efficiency compared with the original DFT. Our finding confirms that the diffusion process within DFT-L propagates fastest in the random network and slowest in the ring-lattice network. We also show that interactions among people affect the agent's decision within DFT-L and intensify embedded society characteristics, which helps to analyze irregular behaviors such as information cascades in social networks.