Reading Personality: Avatar vs. Human Faces

Wang, Yuqiong; Geigel, Joe; Herbert, Andrew M.

doi:10.1109/acii.2013.85

Cited by 17 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Appearance has been observed to be utilized in making interpersonal judgments (Naumann et al, 2009), and this can extend to virtual avatars (Wang et al, 2013;Fong and Mar, 2015). It was observed that judges made relatively consistent inferences based on avatar appearance alone (Wang et al, 2013;Fong and Mar, 2015), and more attractive avatars were rated more highly in an interview scenario (Behrend et al, 2012). How this might manifest with robot avatars, in particular in the interaction between a robot appearance and human voice communication, remains unclear and is yet to be explored.…”

Section: Introductionmentioning

confidence: 99%

Personality Perception of Robot Avatar Teleoperators in Solo and Dyadic Tasks

2017

View full text Add to dashboard Cite

Humanoid robot avatars are a potential new telecommunication tool, whereby a user is remotely represented by a robot that replicates their arm, head, and possible face movements. They have been shown to have a number of benefits over more traditional media such as phones or video calls. However, using a teleoperated humanoid as a communication medium inherently changes the appearance of the operator, and appearance-based stereotypes are used in interpersonal judgments (whether consciously or unconsciously). One such judgment that plays a key role in how people interact is personality. Hence, we have been motivated to investigate if and how using a robot avatar alters the perceived personality of teleoperators. To do so, we carried out two studies where participants performed 3 communication tasks, solo in study one and dyadic in study two, and were recorded on video both with and without robot mediation. Judges recruited using online crowdsourcing services then made personality judgments of the participants in the video clips. We observed that judges were able to make internally consistent trait judgments in both communication conditions. However, judge agreement was affected by robot mediation, although which traits were affected was highly task dependent. Our most important finding was that in dyadic tasks personality trait perception was shifted to incorporate cues relating to the robot's appearance when it was used to communicate. Our findings have important implications for telepresence robot design and personality expression in autonomous robots.

show abstract

Section: Introductionmentioning

confidence: 99%

Personality Perception of Robot Avatar Teleoperators in Solo and Dyadic Tasks

2017

View full text Add to dashboard Cite

show abstract

“…Since ECAs can mimic naturalistic human communication, there are studies comparing human-human interaction with human-ECA interaction. According to Wang, Joel, et al [38], people tended to treat VAs similarly to real human beings. McRorie et al [29] implemented four stereotypical personalities in the virtual agents.…”

Section: Human-eca Impression Formationmentioning

confidence: 99%

Impression Detection and Management Using an Embodied Conversational Agent

Wang

Biancardi

Mancini

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Embodied Conversational Agents (ECAs) are a promising medium for human-computer interaction, since they are capable of engaging users in real-time face-to-face interaction [1, 2]. Users' formed impressions of an ECA (e.g. favour or dislike) could be reflected behaviourally [3,4]. These impressions may affect the interaction and could even remain afterwards [5,7]. Thus, when we build an ECA to impress users, it is important to detect how users feel about the ECA. The impression the ECA leaves can then be adjusted by controlling its non-verbal behaviour [7]. Motivated by the role of ECAs in interpersonal interaction and the state-of-the-art on affect recognition, we investigated three research questions: 1) which modality (facial expressions, eye movements, and physiological signals) reveals most of the formed impressions; 2) whether an ECA could leave a better impression by maximizing the impression it produces; 3) whether there are differences in impression formation during human-human vs. human-agent interaction. Our results firstly showed the interest to use different modalities to detect impressions. An ANOVA test indicated that facial expressions performance outperforms the physiological modality performance (M=1.27, p=0.02). Secondly, our results presented the possibility of creating an adaptive ECA. Compared with the randomly selected ECA behaviour, participants' ratings tended to be higher in the conditions where the ECA adapted its behaviour based on the detected impressions. Thirdly, we found similar behaviour during human-human vs. human-agent interaction. People treated an ECA similarly to a human by spending more time observing the face area when forming an impression.

show abstract

“…It was observed that judges made relatively consistent inferences based on appearance alone [8], [9], and more attractive avatars were rated more highly in an interview scenario [22]. However, how these inferences interact with communicative behaviours of operators has yet to be examined.…”

Section: B Tele-operationmentioning

confidence: 99%

“…This is in light of previous work on personality judgements of virtual avatars based on their appearance [8], [9].…”

Section: Research Questionsmentioning

confidence: 99%