Modelling the Social Interactions in Ant Colony Optimization Nishant Gurrapadi 1[0000−0001−6972−1883] , Lydia Taw 2[0000−0002−4362−9947] , Mariana Macedo 3 * [0000−0002−7071−379X] , Marcos Oliveira 4[0000−0003−3407−5361] , Diego Pinheiro 5[0000−0001−9300−7196] , Carmelo Bastos-Filho 6[0000−0002−0924−5341] , and Ronaldo Menezes 3[0000−0002−6479−6429] 1 Department of Computer Science, University of Texas at Dallas, USA 2 Department of Computer Science, George Fox University, USA 3 BioComplex Lab, Department of Computer Science, University of Exeter, UK * mmacedo@biocomplexlab.org 4 Computational Social Science, GESIS–Leibniz Institute for the Social Sciences, DE 5 Department of Internal Medicine, University of California, Davis, USA 6 Polytechnic School of Pernambuco, University of Pernambuco, BR Abstract. Ant Colony Optimization (ACO) is a swarm-based algorithm inspired by the foraging behavior of ants. Despite its success, the efficiency of ACO has depended on the appropriate choice of parameters, requiring deep knowledge of the algorithm. A true understanding of ACO is linked to the (social) interactions between the agents given that it is through the interactions that the ants are able to explore-exploit the search space. We propose to study the social interactions that take place as artificial agents explore the search space and communicate using stigmergy. We argue that this study bring insights to the way ACO works. The interaction network that we model out of the social interactions reveals nuances of the algorithm that are otherwise hard to notice. Examples include the ability to see whether certain agents are more influential than others, the structure of communication, to name a few. We argue that our interaction-network approach may lead to a unified way of seeing swarm systems and in the case of ACO, remove part of the reliance on experts for parameter choice. Keywords: Swarm Intelligence · Swarm-based algorithms · Ant Colony Opti- mization · Interaction network · Social interactions. 1 Introduction Swarm intelligence algorithms have been successfully applied to solve a wide range of optimization problems due to the simultaneous use of multiple artificial agents on high dimensional search problems [5,4]. Even though they are effective, the usability of swarm-based algorithms is limited by the lack of knowledge on why the interaction of simple reactive agents lead to such a complex system. Another challenge is the diversity of algorithms inspired by different animals such as ants, bees, fish, wolves and birds. Knowing what is the best swarm-based algorithm and its initialization to each type of problem requires deep expertise.