Gender stereotypes in virtual agents

Visual, behavioural and verbal cues for gender are often used in designing virtual agents to take advantage of their cultural and stereotypical effects on the users. However, recent studies point towards a more gender-balanced view of stereotypical traits and roles in our society. This thesis is intended as an effort towards a progressive and inclusive approach for gender representations in virtual agents. The contributions are two-fold. First, in an iterative design process, representative male, female and androgynous embodied AI agents were created with few differences in their visual attributes. Second, these agents were then used to evaluate the stereotypical assumptions of gendered traits and roles in AI virtual agents. The results showed that, indeed, gender stereotypes are not as effective as previously assumed, and androgynous agents could represent a middle-ground between gendered stereotypes. The thesis findings are presented in the hope to foster discussions in virtual agent research and the frequent stereotypical use of gender representations.