Use Of Virtual Agents Research Articles

Virtual agents that flatter you: Moderating effects of self‐esteem and customization target in e‐customization services

AbstractAs e‐customization services have grown in popularity, companies widely use virtual agents in such services to improve consumers' online shopping experience. However, extant research has not thoroughly clarified the best way to leverage the use of virtual agents and involve consumers in the e‐customization process. Drawing on self‐enhancement and self‐verification theories, this research investigates the effects of an instrumental social influence tactic employed by virtual agents—specifically, flattering feedback—and the pivotal roles of consumers' self‐esteem and customization target when evaluating and using e‐customization services. Through four experiments that simulate e‐customization experiences using different products, we find that the effect of virtual agents' flattering feedback on customization outcomes (i.e., word‐of‐mouth, product interest, and actual purchase) is contingent on consumers' self‐esteem. Among consumers with high self‐esteem, flattering (vs. generic) feedback from virtual agents in the e‐customization process elicits more positive customization outcomes. In contrast, the opposite is true among those with low self‐esteem. Moreover, consumers' process involvement mediates the interaction effects, and the interaction effects are attenuated when consumers customizing the product for others (vs. oneself). Our work contributes to online customization research by unveiling the mechanism and boundary conditions of the potentially double‐edged effect of virtual agents' flattery.

Customer Service Combining Human Operators and Virtual Agents: A Call for Multidisciplinary AI Research

The use of virtual agents (bots) has become essential for providing online assistance to customers. However, even though a lot of effort has been dedicated to the research, development, and deployment of such virtual agents, customers are frequently frustrated with the interaction with the virtual agent and require a human instead. We suggest that a holistic approach, combining virtual agents and human operators working together, is the path to providing satisfactory service. However, implementing such a holistic customer service system will not, and cannot, be achieved using any single AI technology or branch. Rather, such a system will inevitably require the integration of multiple and diverse AI technologies, including natural language processing, multi-agent systems, machine learning, reinforcement learning, and behavioral cloning; in addition to integration with other disciplines such as psychology, business, sociology, economics, operation research, informatics, computer-human interaction, and more. As such, we believe this customer service application offers a rich domain for experimentation and application of multidisciplinary AI. In this paper, we introduce the holistic customer service application and discuss the key AI technologies and disciplines required for a successful AI solution for this setting. For each of these AI technologies, we outline the key scientific questions and research avenues stemming from this setting. We demonstrate that integrating technologies from different fields can lead to a cost-effective successful customer service center. The challenge is that there is a need for several communities, each with its own language and modeling techniques, different problem-solving methods, and different evaluation methodologies, all of which need to work together. Real cooperation will require the formation of joint methodologies and techniques that could improve the service to customers, but, more importantly, open new directions in cooperation of diverse communities toward solving joint difficult tasks.

Simulating Social Emotion Regulation in Virtual Reality

Virtual reality (VR) is a valuable research tool offering advantages in terms of high experimenter control and standardization in the simulation of vivid personal and social experiences. It has been used for assessments and training in social cognition with the use of virtual agents instead of face-to-face interactions – but its potential for the study of social emotion regulation has, perhaps surprisingly, largely remained untapped. The present study evaluates a novel immersive VR scenario designed to study the efficacy of social support by a virtual agent using a modified version of Cyberball, an established paradigm to induce the feeling of ostracism. Participants embodied a new pupil in a virtual school environment and played Cyberball, after which they either did or did not receive emotional support. Self-reports and psychophysiological markers demonstrated that the negative impact of social exclusion in Cyberball was successfully replicated, while participants also reported a significant improvement in emotional state after being supported by the virtual agent. These results indicate the potential of the developed scenario for research on social emotion regulation in immersive VR. Future studies could aim to test the efficacy of social support for people with difficulties in self-regulation, for example individuals with high social anxiety, with a view to developing training programs in VR.

Buffer bots: The role of virtual service agents in mitigating negative effects when service fails

AbstractIn recent years, marketers have placed increased reliance upon artificial intelligence (AI) and, subsequently, the use of virtual agents in customer service contexts is on the rise. Despite such service digitalization, service can still fail. While there is an increasing literature on the effect of virtual agents in service settings, questions remain as to how customers react to service failure that results from interactions with virtual service agents. To this end, we deconstruct the effect of virtual agent service failure across two studies: one involving a process service failure and another involving an outcome service failure. We specifically manipulate the type of service agent that causes the service failure (human vs. virtual agent) and the magnitude of the failure (small vs. large). Results show that firms can leverage virtual service agents to mitigate or buffer the negative effects of service failure. From a managerial perspective, our findings suggest that firms could engage virtual service agents in situations where there may be a risk of outcome service failure—particularly in settings where relatively large magnitude failures may be experienced. In such a setting, we find that virtual service agents can mitigate the negative effects of service failure, more so than when the failure results from an interaction with a human service agent.

Age-Related Differences in the Evaluation of a Virtual Health Agent's Appearance and Embodiment in a Health-Related Interaction: Experimental Lab Study.

BackgroundAssistive technologies have become more important owing to the aging population, especially when they foster healthy behaviors. Because of their natural interface, virtual agents are promising assistants for people in need of support. To engage people during an interaction with these technologies, such assistants need to match the users´ needs and preferences, especially with regard to social outcomes.ObjectivePrior research has already determined the importance of an agent’s appearance in a human-agent interaction. As seniors can particularly benefit from the use of virtual agents to maintain their autonomy, it is important to investigate their special needs. However, there are almost no studies focusing on age-related differences with regard to appearance effects.MethodsA 2×4 between-subjects design was used to investigate the age-related differences of appearance effects in a human-agent interaction. In this study, 46 seniors and 84 students interacted in a health scenario with a virtual agent, whose appearance varied (cartoon-stylized humanoid agent, cartoon-stylized machine-like agent, more realistic humanoid agent, and nonembodied agent [voice only]). After the interaction, participants reported on the evaluation of the agent, usage intention, perceived presence of the agent, bonding toward the agent, and overall evaluation of the interaction.ResultsThe findings suggested that seniors evaluated the agent more positively (liked the agent more and evaluated it as more realistic, attractive, and sociable) and showed more bonding toward the agent regardless of the appearance than did students. In addition, interaction effects were found. Seniors reported the highest usage intention for the cartoon-stylized humanoid agent, whereas students reported the lowest usage intention for this agent. The same pattern was found for participant bonding with the agent. Seniors showed more bonding when interacting with the cartoon-stylized humanoid agent or voice only agent, whereas students showed the least bonding when interacting with the cartoon-stylized humanoid agent.ConclusionsIn health-related interactions, target group–related differences exist with regard to a virtual assistant’s appearance. When elderly individuals are the target group, a humanoid virtual assistant might trigger specific social responses and be evaluated more positively at least in short-term interactions.

Language, modality, and mobile media use experiences: Social responses to smartphone cues in a task-oriented context

With people’s growing use of virtual agents and voice assistants on smartphones, researchers have pointed out that mobile phones are not only acting as intermediaries that connect users from different places, but also communication terminals that present different combinations of social cues. This study applies the Computers are Social Actors paradigm in human-phone interaction and postulates that compared to non-anthropomorphic language and text cues, anthropomorphic language and vocal cues will have more effects on users’ social responses to smartphones. This study also explores the role of individual differences in users’ social responses to smartphones. Based on a lab experiment using a between-subjects factorial design, the study suggests that although anthropomorphic language and voice-based information did not have main effects on users’ social responses, people’s mobile media usage and intensive phone use interacted with these cues in their social responses to the smartphones. In addition, this study implies that it is the combination of social cues, individual differences, and communication contexts that contributes to people’s social reactions to the smartphones. The findings of the study can inform user interface design and precipitate further discussion about the ethical issues in human-phone interaction.

Advantages of virtual agents over clinical psychologists during comprehensive mental health interviews using a mixed methods design

The use of Virtual Agents (VAs) is currently a popular topic in mental health interviews. Advantages of VA over Real Expert (RE) in the interview were reported. However, the advantages of audio-visual VAs over REs during comprehensive mental health interviews remain unclear, and their clarification is important to promote the practical application of VAs in these settings. To explore the advantages, we triangulated data using mixed methods design, aiming to show quantitative advantages of the VAs in their perceived rapport and eye movement, and to describe the qualitative advantages of the VAs in their disclosed mental symptoms during the interview. A total of 55 Japanese university students participated in comprehensive mental health interviews conducted by the VA and RE. Findings show that participants perceived rapport and moved their right eyes more often, along with disclosing numerous mental symptoms, with the RE than the VA. However, they disclosed more sex-related symptoms to the VA than the RE. The VA can be used most practically in sex-related health fields. The anonymity conditions in the VA setting might be relevant to patients' self-disclosure of sex-related topics.

Linguistic and emotional feedback for self-tracking physical activity

The level of physical activity is one of the most important parameters to monitor the evolution of some physical and mental disorders, e.g., obesity or depression. Its continuous monitoring provides an objective and quantitative measurement tool to be applied by therapists when developing patient-specific treatments. Most of existing activity recognition systems have been developed using multiple accelerometers strapped to the subject’s extremities. In this paper, we design an interpretable and transparent model able to describe the basic physical activity and the energy requirements of a person, by capturing the accelerations of its smartphone placed wherever he/she wants. In addition, the use of virtual agents that interact and communicate relevant information in an emotional way, increases the effectiveness and acceptance of the Human Computer Interfaces. Thus, we develop a computational application that combines activity recognition techniques with affective computing ones. We include first experimental results that demonstrate the potential and applicability of this tool.

Pedagogical psychology: beyond the 21st century.

Pedagogical psychology: beyond the 21st century.

The Emerging Role of Artificial Intelligence in the Study and Practice of Negotiation & Mediation

This symposium explores how the rapidly growing field of artificial intelligence might transform the way we study and practice negotiation and mediation. Four presentations by leading scholars at the nexus of computer science and psychology explore new research tools, innovative paradigms, and insights for the fields of negotiation and dispute resolution. By analyzing negotiation behavior in the cloud, we streamline the process of collecting large quantities of nonverbal data efficiently, and generate findings on the role of facial expressions and paralinguistic features, such as speaking rate, turn- taking, and volume. We present results from a study on the use of virtual agents to shed light on negotiator characteristics, such as gender and race. Using an avatar as a mediator of an online dispute, we demonstrate how mimicry by the mediator leads to disputants becoming more conciliatory. Finally, we discuss both advantages and disadvantages of introducing artificial intelligence in the context of negotiation and mediation. Taken together, results offer advances for both researchers and practitioners alike. Processing Negotiation Behavior in the Cloud Presenter: Michelle Fung; U. of Rochester Presenter: Jared R. Curhan; Massachusetts Institute of Technology Presenter: Mohammed Ehsan Hoque; U. of Rochester Virtual Confederates in the Study of Negotiation Presenter: Celso M. de Melo; U. of Southern California Presenter: Peter J. Carnevale; U. of Southern California Presenter: Jonathan Gratch; U. of Southern California Barriers to the Effective Use of Artificial Intelligence in Online Dispute Resolution Presenter: John Zeleznikow; Victoria U.

Attractive Agents Are More Persuasive

Advances in more ubiquitous human–computer interface technologies have resulted in the increased use of virtual agents, thus highlighting the need to understand the impact these artificial entities have on the human user in terms of how the user both perceives and behaves toward these characters. We report the results of an experiment based on the Desert Survival task, where the effect of agent attractiveness on persuasion was tested. The results suggest that the attractive agent was significantly more persuasive in changing the participant's opinion than was the unattractive agent. Furthermore, greater behavioral change was observed when the participant interacted with the attractive agent, in terms of persuasiveness, including the attribution of more positive personality traits toward this agent (the attractiveness stereotype). These findings provide further evidence of the powerful influence of the agent's physical appearance on the human user in an interaction-based context. We conclude by pointing toward future research and potential within the area.

Creation of a new set of dynamic virtual reality faces for the assessment and training of facial emotion recognition ability

The ability to recognize facial emotions is target behaviour when treating people with social impairment. When assessing this ability, the most widely used facial stimuli are photographs. Although their use has been shown to be valid, photographs are unable to capture the dynamic aspects of human expressions. This limitation can be overcome by creating virtual agents with feasible expressed emotions. The main objective of the present study was to create a new set of dynamic virtual faces with high realism that could be integrated into a virtual reality (VR) cyberintervention to train people with schizophrenia in the full repertoire of social skills. A set of highly realistic virtual faces was created based on the Facial Action Coding System. Facial movement animation was also included so as to mimic the dynamism of human facial expressions. Consecutive healthy participants (n = 98) completed a facial emotion recognition task using both natural faces (photographs) and virtual agents expressing five basic emotions plus a neutral one. Repeated-measures ANOVA revealed no significant difference in participants’ accuracy of recognition between the two presentation conditions. However, anger was better recognized in the VR images, and disgust was better recognized in photographs. Age, the participant’s gender and reaction times were also explored. Implications of the use of virtual agents with realistic human expressions in cyberinterventions are discussed.

Sekab defends technology for making ethanol from cellulose

The level of physical activity is one of the most important parameters to monitor the evolution of some physical and mental disorders, e.g., obesity or depression. Its continuous monitoring provides an objective and quantitative measurement tool to be applied by therapists when developing patient-specific treatments. Most of existing activity recognition systems have been developed using multiple accelerometers strapped to the subject’s extremities. In this paper, we design an interpretable and transparent model able to describe the basic physical activity and the energy requirements of a person, by capturing the accelerations of its smartphone placed wherever he/she wants. In addition, the use of virtual agents that interact and communicate relevant information in an emotional way, increases the effectiveness and acceptance of the Human Computer Interfaces. Thus, we develop a computational application that combines activity recognition techniques with affective computing ones. We include first experimental results that demonstrate the potential and applicability of this tool.