What is in three words? Exploring a three-word methodology for assessing impressions of a social robot encounter online and in real life

Abstract

We explore the impressions and conceptualisations produced by participants after their first encounter with the teleoperated robot, Telenoid R1.Participants were invited to freely report the first three words that came to mind after seeing the robot. Here we triangulate (i) three-word data from an online survey (n=340) where respondents saw a brief video of the Telenoid with (ii) three-word data from an interaction study where participants interacted with a physically present Telenoid (n=75) and, (iii) data from qualitative interviews (n=7) with participants who had engaged with the Telenoid. Data were subjected to sentiment analysis, linguistic analysis and regression analysis.Ranking of the most frequently produced words in the two groups revealed an overlap on the top-10 produced words (6 out of 10 words). Sentiment analysis and regression revealed an association between negative predicates and the online condition. Sentiments were not convincingly associated with age or gender. Linguistic categorisations of the data revealed that especially adjectives expressing response-dependent features were frequent. We did not find any consistent statistical effect on categorising the words into cognitive and emotional predicates.The proposed three-word method offers, unguided approach to explore initial conceptualisations of robots.

The Sounds of Softness. Designing Sound for Human-Soft Robot Interaction

“…In Experiment 1, gender (p 0.054) and age (p 0.066) had marginal effects on whether a participant used a word with a positive sentiment to describe the robot. Male participants appear less likely to use a word with positive sentiment and the direction of the latter relationship matches the results obtained by Damholdt et al (2019), where an increase in age led to a higher probability that participants would use a word with positive sentiment. This marginal effect might become significant with a wider age range, and not all but one participant being university students, as in our cohort.…”

“…Before filling out the RoSAS scale, participants were asked to "Write the first three words that come to mind to describe the robot that you have just experienced," following the method proposed by Damholdt et al (2019). Another scale question was added after the RoSAS scale: "Using the scale provided, please indicate to which extent you agree with the following statement about the robot: 'The robot has a sound that is appropriate for it'" (1-Strongly agree, 7-Strongly disagree).…”

“…Following the method described in (Damholdt et al, 2019), we used logistic regression to determine if the words used to describe the robots had different distributions of sentiment in the three sound conditions for each robot. We used this method of analysis to determine if the sound design condition could predict the likelihood that respondents would report a word with a positive sentiment.…”

“…The three response items from one participant who had used the three words to form one coherent entry ("star," "wars," "sounds") were reduced to two items ("star wars" and "sounds") and a blank entry, yielding a reduction to 377 items. As the next step, all Danish items were translated into English and items containing more than one word were shortened to one word, following the procedure in (Damholdt et al, 2019). Two coders then coded all words as being of either negative, neutral, or positive sentiment.…”

Who is Best at Mediating a Social Conflict? Comparing Robots, Screens and Humans

“…The mediation experiment reported in this article was motivated by the advent of new interactive technologies and suggestive findings from early research on their impacts. [See the review of these technologies by Druckman and Koszegi (2017) and Damholdt et al (2019).] Taking advantage of recent advances in technologies, we discerned an opportunity to let the research lines on e-mediation (Druckman et al 2014) and human-robot interaction (see Goodrich and Schultz 2007) cross in new ways.…”