Perception of Power and Distance in Human-Human and Human-Robot Role-Based Relations

Abstract

The use and interpretation of social linguistic strategies such as politeness is influenced by multiple factors, e.g., the speaker-hearer relation. Such relations influence an interlocutor's expectations regarding the interaction and thus also its perception. This makes speaker-hearer relations constituting a partner model highly relevant for the user experience in human-robot interaction as well. This paper presents a questionnaire-based study on the perception of human-robot relations in comparison to human-human relations across different roles (e.g., colleague, assistant) and spaces of interaction (home, work, public). It was found that participants perceive robots differently based on space, as they do for human-human relations in corresponding roles. Overall, humans were evaluated to have more power over and more distance to a robot interaction partner compared to another human. Our results provide insights into an intuitive interactioninitial partner model based on roles.

Should robots be polite? Expectations about politeness in human–robot interaction

“…Further, participants were also not aware that they would have the opportunity to interact with the robot at the end of the interview. Based on Lumer and Buschmeier (2022) , who found influences of different space and roles of robots on their perceived relation to users, we included three different spatial scenarios, to further elicit discussions on the influences of location based role differences (at home, at work, in public) on politeness. The experimental setup (with the robot revealed) is shown in Figure 1 .…”

Modeling Politeness in Human-Robot Interaction

“…To gain further insights on politeness in HRI, I considered different perspectives by applying a range of research and evaluation methods including quantitative and qualitative methods. I first collected data with a quantitative online study [16]. This study was insightful, but limited to pre-defined categories due to its methodology.…”

“…Relevant influences on politeness that I plan to consider in my model include gender [10], mood [27], emotion [25,27], situation [3,14], and power and distance [3]. Further, based on earlier results [16], for the implementation I will also control the role that the robot is presented in, as the role determines the user's relationship with the robot. Building on previous small-scale Bayesian modeling of politeness [15], this probabilistic Bayesian model will choose a politeness strategy based on the parameter setting of the different influences.…”

Indirect Politeness of Disconfirming Answers to Humans and Robots

“…Additionally, as Brown and Levinson [10] and others [12] suggest that power and distance influence the choice of politeness strategy, we also queried participants' evaluation of their power over the robot and their perceived distance to it. Based on previous research [22], we expect participants to feel generally distanced towards the robot and to not have much power over them.…”

“…Participants evaluated their perceived power over and distance to the robot (using the questions of Lumer and Buschmeier [22]). Participants evaluated their power over the robot to be 48.3 on average (Mdn = 49, SD = 21.2) on a scale from 0 (low authority) to 100 (high authority).…”