Exploiting Reverse Correlation for the Generation of Virtual Characters from Personality Traits

Judging from appearance, most people assign personality traits to virtual characters. This paper presents a platform capable of generating online Reverse Correlation experiments for studying the relations between the appearance of virtual characters and their assumed personality. The method used by the platform, which leverages crowdsourcing and interactive genetic algorithms, can be used to generate virtual characters starting from a description of their personality. The platform requires a training phase to gather the beliefs and convictions that people have when judging a person from his/her appearance. The method is validated through two experiments. The first experiment provides evidence on how effective the method is in improving the mapping through genetic evolution. The second experiment illustrates how the method relates to the technique of Reverse Correlation to infer which physical attributes contribute to the perception of a specific trait.