How the agent's gender influence users' evaluation of a QA system

Abstract

Abstract--In this paper we present the results of a pilot study investigating the effects of agents' gender-ambiguous vs. gendermarked look on the perceived interaction quality of a multimodal question answering system. Eight test subjects interacted with three system agents, each having a feminine, masculine or gender-ambiguous look. The subjects were told each agent was representing a differently configured system. In fact, they were interacting with the same system. In the end, the subjects filled in an evaluation questionnaire and participated in an in-depth qualitative interview. The results showed that the user evaluation seemed to be influenced by the agent's gender look: the system represented by the feminine agent achieved on average the highest evaluation scores. On the other hand, the system represented by the gender-ambiguous agent was systematically lower rated. This outcome might be relevant for an appropriate agent look, especially since many designers tend to develop gender-ambiguous characters for interactive interfaces to match various users' preferences. However, additional empirical evidence is needed in the future to confirm our findings.

Robots and Gender

“…In a comparison experiment between a mechanical humanoid robot and an android with a female appearance, Carpenter and her colleagues 10 suggested that participants (19 university students in the United States; male N = 9; female N = 10) preferred the female robot for in-home use. Niculescu and her colleagues 11 conducted an evaluation experiment (N = 8) for Question & Answer (QA) systems with computer graphic (CG) characters on a computer screen (so-called virtual robots or agents) with three types of heads: feminine; masculine; and gender-ambiguous. The researchers found that participants were more comfortable, more confident, and less tense when using the system with the feminine character, compared with the other systems.…”

Team Structure and Team Building Improve Human–Machine Teaming With Autonomous Agents

“…Researchers have extended Nass and colleagues’ (1997) work on robots as social actors in a variety of ways. First, there have been explorations into how a robot’s gender can influence social responses (e.g., Niculescu, Hofs, van Dijk, & Nijholt, 2010; Powers & Kiesler, 2006). The emotional assessment and expression of robots during social interaction is another area of interest (e.g., Breazeal, 2003).…”

Exploring Virtual Agents for Augmented Reality

“…We also did not look at if the gender of the virtual agent had an impact on users' behaviors and perceptions. Prior work has shown some preference to female embodied agents [24,41,50,62], while others have found no difference in preference [20,32] or a preference for male agents [40]. However, these studies were specifically looking at factors such as credibility or likeability, which was not our research emphasis.…”