出版社：The Japanese Society for Artificial Intelligence
摘要：It is often the case that a single person belongs to multiple communities and expresses different opinions by community. However, the lack of consistency of his opinions is subject to criticism when they are uncovered. Recently, opinion formation mainly occurs in online communities instead of real communities and this affects the opinion formation environment as follows: 1) the inconsistency of opinions is easily disclosed because many online communities are not closed, and 2) there are some people too sensitive to such inconsistency. These become social pressures making people rather silent in communities and cause many phenomena including silent majority/vocal minority and opinion polarization. It is important to clarify how these changes affect opinion formation processes. Our goal is to reveal the dynamics of opinion formation in multiple communities, considering the dilemma of people between the adaptation to each of communities and the lack of consistency. We make an agent based model based on the Bounded Confidence Model on multiplex network structures. The model is novel in considering conflict between agent's different opinions across multiple communities. As a result of simulation, it is found that probability of disclosure of the lack of consistency could cause opinion formation processes differently by how agents are sensitive to the lack of consistency. Only when agents do not overreact to the lack of consistency, the larger the probability of disclosure is, the smaller the variation of opinions within communities becomes. On the other hand, when agents overreact to the lack of consistency, the mechanism of opinion formation is different. Furthermore, we reveal the mechanism of the influence of social pressure to the opinion formation processes. These results can explain real world phenomena and offer suggestions for the facilitation of consensus formation in the age of Internet.
关键词：Opinion Dynamics ; Multiplex Network ; Agent Based Simulation
