Emojinating: Evolving Emoji Blends Jo˜ ao M. Cunha, Nuno Louren¸co, Jo˜ ao Correia, Pedro Martins, and Penousal Machado CISUC, Department of Informatics Engineering University of Coimbra {jmacunha,naml,jncor,pjmm,machado}@dei.uc.pt Abstract. Graphic designers visually represent concepts in several of their daily tasks, such as in icon design. Computational systems can be of help in such tasks by stimulating creativity. However, current compu- tational approaches to concept visual representation lack in effectiveness in promoting the exploration of the space of possible solutions. In this paper, we present an evolutionary approach that combines a standard Evolutionary Algorithm with a method inspired by Estimation of Distri- bution Algorithms to evolve emoji blends to represent user-introduced concepts. The quality of the developed approach is assessed using two separate user-studies. In comparison to previous approaches, our evo- lutionary system is able to better explore the search space, obtaining solutions of higher quality in terms of concept representativeness. Keywords: Evolutionary Algorithm · Emoji · Interactive Evolutionary Computation · Visual Blending . 1 Introduction In the domain of visual representations, computers have been made to draw on their own (e.g. [1]), used as creativity support tools for drawing (e.g. [2]) and even been given the role of colleague in co-creative systems (e.g. [3]). These examples, however, are more related to Art and shift away from the Design domain, in which a specific problem is addressed – e.g. how to design an icon to represent a given concept. The difficulty behind developing computational approaches to solve Design problems is that, in most cases, they greatly depend on human perception. For this reason, they can be seen as open-ended as there is no optimal solution since they hinge on the user preferences. Thus, assessing quality is a complex problem on its own. One possible way to tackle this problem is to develop a system that allows the user to choose which solutions are adequate. One of such approaches in the Evolutionary Computation domain is usually referred to as Interactive Evolutionary Computation (iec). iec has been seen as suitable for such open- ended design problems [4], since it is capable of accumulating user preferences and, at the same time, stimulating creativity. Regarding the visual representation of concepts, a multi-purpose system has great potential to be used as an ideation-aiding tool for brainstorming activities,