Gamers and non-gamers preferences ofcrossmodal AI assistants : A remote explorative study on the uncanny

Abstract: Technological advancements have allowed the design of more realistic virtual characters, for example, in-game development; meanwhile, researchers argue that more realism is not always suitable. As an explorative pilot study, this thesis investigates the uncanny among human-like agents and intelligent systems with human-like attributes. The thesis focuses on the uncanny theories to understand whether Mori's Uncanny Valley (UV) or Tinwell's Uncanny wall (UW) is more suitable when designing with a user-centred approach. The study facilitated two remote focus group workshops consisting of seven participants to understand the participant's expectations, needs and desires of existing and future AI technology. The participants consisted of two target groups, gamers and non-gamers, in order to understand if exposure to AI leads to adoptability of the technology. The participants described their perspectives and needs of existing AI assistants, and their preferences of human-like cross modality such as voice and avatar for future assistants. The research activities resulted in insights and four themes: rejection of existing assistant technology, productivity and task management, expectations of future AI assistants and balancing human-likeness. Findings show that participants reject existing assistant technologies, as old tangible habits, social norms, and incompatibility prevent the adoption of existing assistant technology. While both gamers and non-gamers seek a balance between generic robotics and pure human likeness, none of the participants fully adopted the idea of human likeness as it generates uncanny feelings.