Peng Lu and his colleagues explored Individual behaviors, social learning, and swarm intelligence by using a real case and counterfactuals

November 30, 2022, Prof. Peng Lu and his colleagues published a paper on Expert Systems With Applications. In this paper, they use the mass shooting case, as a typical category of common risks (social disasters), and use two-round simulations to achieve the research goal which is to calculate social knowledge, based on which social welfare can be enhanced, and to use social knowledge to improve social welfare.

Abstract:It is hard for individuals to handle social common risk, such as terrorism attacks (mass shooting). However, it can be contained, if they can be organized and behave intelligently. To obtain this swarm intelligence pattern, social knowledge should be captured to guide behaviors of isolated individuals. Here, we explore how swarm intelligence can be achieved by individual behaviors during social learning process. We have solved two issues. The first is to obtain social knowledge. Based on agent-based model of real target case, we calculate the optimal solution based on which we infer outcomes of all possible situations. Then, the matrix of social knowledge can be formed; The second is social learning process of individuals. Guided by the social knowledge, they all know that others will be mobilized as well. The key information is the minimal valid size of heroes, and all social members know that this condition is not difficult to satisfy. Thus, more individuals will be mobilized and become the Heroes to fight bravely against the shooter(s). Comparing two patterns, we obtain precise outcomes of how social losses (civilian deaths and injuries) can be reduced. Therefore, guided by clear social knowledge, social welfare can be enhanced substantially.

Keywords: Social knowledge;Agent-based model;Swarm intelligence;Counterfactuals

Fig. 1. Real case and other scenarios settings. Panel A is real scene, and the shooter entered and fired through exit 1. The red line refers to first round of shooting, and blue solid line refers to second-round of shooting. The blue dashed line is the retreat route of the shooter. Subfigures B-F refer to 5 counterfactual settings. (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

Fig. 2. Social Learning Algorithm. The blue matrix is the payoff matrix, with values of survival chances (rates) for three groups. The purple matrix is the risk matrix, with values death risks for three groups. The two matrices are complementary for each other. Both valid boundary and death risks will increase the probability of civilians to be the hero. After social learning, the survival chances (rates) of civilians will be enhanced, which is indicated by the boxplot (K-line diagram). (For interpretation of the references to colour in this figure legend, the reader is referred to the web version of this article.)

2022年11月30日,国际权威学术期刊《Expert Systems with Applications》第207在线发表吕鹏和合作者的研究论文“Individual behaviors, social learning, and swarm intelligence: Real case and counterfactuals”。



Lu Peng, et al.”Individual behaviors, social learning, and swarm intelligence: Real case and counterfactuals.” Expert Systems With Applications 207.(2022). doi:10.1016/J.ESWA.2022.117878.

This article was last updated on days ago, and the information described in the article may have changed.