Mind the Eyes: Artificial Agents’ Eye Movements Modulate Attentional Engagement and Anthropomorphic Attribution

Abstract

Artificial agents are on their way to interact with us daily. Thus, the design of embodied artificial agents that can easily cooperate with humans is crucial for their deployment in social scenarios. Endowing artificial agents with human-like behavior may boost individuals’ engagement during the interaction. We tested this hypothesis in two screen-based experiments. In the first one, we compared attentional engagement displayed by participants while they observed the same set of behaviors displayed by an avatar of a humanoid robot and a human. In the second experiment, we assessed the individuals’ tendency to attribute anthropomorphic traits towards the same agents displaying the same behaviors. The results of both experiments suggest that individuals need less effort to process and interpret an artificial agent’s behavior when it closely resembles one of a human being. Our results support the idea that including subtle hints of human-likeness in artificial agents’ behaviors would ease the communication between them and the human counterpart during interactive scenarios.

Effects of robot gaze and voice human-likeness on users’ subjective perception, visual attention, and cerebral activity in voice conversations

“…Perugia, Paetzel-Prüsmann, Alanenpää, and Castellano (2021) compared users' total fixation time toward human-like, mechanical, or morph robot faces with mutual gaze and found that users'total fixation time could predict engagement in voice conversations. Users' visual attention toward the human gaze versus the robot gaze with different parameters also has been explored by watching videos (Ghiglino et al, 2020(Ghiglino et al, , 2021.…”

“…Additionally, these earlier studies chiefly measured users' subjective perception (Babel et al, 2021;Morillo-Mendez et al, 2021;Mutlu et al, 2012) or combined with either visual attention (Ghiglino et al, 2020(Ghiglino et al, , 2021Thepsoonthorn et al, 2021) or cerebral activity (Belkaid et al, 2021;Kompatsiari, Bossi, & Wykowska, 2021). Kelley et al (2021) measured eye movements with brain signals and reported the proportion of time spent looking at robot eyes and cerebral activity.…”

Belief in sharing the same phenomenological experience increases the likelihood of adopting the intentional stance towards a humanoid robot

“…before any task is given to participants). Furthermore, recently Ghiglino and colleagues showed that subtle differences in the robot behavior might influence the individual tendency to adopt the intentional stance (Ghiglino et al, 2020) and that including human-like behaviors in the robot can facilitate communication in human-robot interaction in interactive scenarios (Ghiglino et al, 2021).…”

Fintech Agents: Technologies and Theories

“…This form factor allows clients to have more natural face-to-face conversations at any time, combining the features of human interaction with the benefits of agent interaction. Furthermore, the inclusion of human-like behaviors such as eye movements has the potential to boost users' communication with agents [170].…”