The Proteus effect describes how users of virtual environments adjust their attitudes to match stereotypes associated with their avatar's appearance. While numerous studies have demonstrated this phenomenon's reliability, its underlying processes remain poorly understood. This work investigates deindividuation's hypothesized but unproven role within the Proteus effect. Deindividuated individuals tend to follow situational norms rather than personal ones. Therefore, together with high embodiment and identification processes, deindividuation may lead to a stronger Proteus effect. We present two experimental studies. First, we demonstrated the emergence of the Proteus effect in a real-world academic context: engineering students got better scores in a statistical task when embodying Albert Einstein's avatar compared to a control one. In the second study, we tested the role of deindividuation by manipulating participants' exposure to different identity cues during the task. While we could not find a significant effect of deindividuation on the participants' performance, our results highlight an unexpected pattern, with embodiment as a negative predictor and identification as a positive predictor of performance. These results open avenues for further research on the processes involved in the Proteus effect, particularly those focused on the relation between the avatar and the nature of the task to be performed. All supplemental materials are available at https://osf.io/au3wk/.

Empathic behavior between humans often has a positive effect, particularly in healthcare, since it facilitates relationships, improves engagement, and reduces stress and anxiety. Despite the importance of empathic communication and social relationship in healthcare, effects of empathic behavior of embodied virtual agents that interact with patients in a multimodal and adaptive way have not been widely explored. In this article, we propose an empathic model which endows a therapeutic embodied virtual agent with multi-modal adaptive empathic behavior during interaction with a user. This model relies on the user-agent interaction relationship and focuses on (1) the interpretation of user's behavior using multimodal input, and (2) the generation of multimodal empathic behavior during interaction. An experimental study in the context of empathic interaction with students during the COVID-19 pandemic is presented to evaluate the effects of adaptive empathic behavior of an agent on the quality of user interaction. Compared to an agent that relies on low-level affect matching and backchannels, results show that our agent is perceived as more empathic and improves user engagement during the interaction.

Empathic behavior between humans often has a positive effect, particularly in healthcare, since it facilitates relationship, improves engagement, and reduces stress and anxiety. Despite this importance of empathic communication and social relationship in healthcare, the effects of empathic behavior of embodied virtual agents that interact with patients in a multimodal and adaptive way have not been widely explored. The proposed multimodal adaptive empathic agent architecture (MAEAA) endows a therapeutic embodied virtual agent (EVA) with adaptive empathic behavior during interaction with a user. This architecture relies on user-agent interaction relationship and focuses on (1) the interpretation of user's behavior using multimodal input, and (2) the generation of multimodal empathic behavior during interaction. The solution have been used to develop a user study for the empathic interaction with students in the healthcare context [3].

Group cohesion is an emergent phenomenon that describes the tendency of the group members’ shared commitment to group tasks and the interpersonal attraction among them. This paper presents a multimodal analysis of group cohesion using a corpus of multi-party interactions. We utilize 16 two-minute segments annotated with cohesion from the AMI corpus. We define three layers of modalities: non-verbal social cues, dialogue acts and interruptions. The initial analysis is performed at the individual level and later, we combine the different modalities to observe their impact on perceived level of cohesion. Results indicate that occurrence of laughter and interruption are higher in high cohesive segments. We also observe that, dialogue acts and head nods did not have an impact on the level of cohesion by itself. However, when combined there was an impact on the perceived level of cohesion. Overall, the analysis shows that multimodal cues are crucial for accurate analysis of group cohesion.

Addressee detection is an important challenge to tackle in order to improve dialogical interactions between humans and agents. This detection, essential for turn-taking models, is a hard task in multiparty conditions. Rule based as well as statistical approaches have been explored. Statistical approaches, particularly deep learning approaches, require a huge amount of data to train. However, smart feature selection can help improve addressee detection on small datasets, particularly if multimodal information is available. In this article, we propose a statistical approach based on smart feature selection that exploits contextual and multimodal information for addressee detection. The results show that our model outperforms an existing baseline.

Addressee detection is one of the most fundamental tasks for seamless dialogue management and turn taking in human-agent interaction. Whereas addressee detection is implicit in dyadic interaction, it becomes a challenging task in multiparty interactions when more than two participants are involved. Existing research works employ either rule-based or statistical approaches for addressee detection. However, most of these works either have been tested on a single data set or only support a fixed number of participants. In this article, we propose a model based on generic features to predict the addressee in data sets with varying number of participants. The results tested on two different corpora show that the proposed model outperforms existing baselines.

Automatic dialogue act annotation of speech utterances is an important task in human-agent interaction in order to correctly interpret user utterances. Speech utterances can be transcribed manually or via Automatic Speech Recognizer (ASR). In this article, several Machine Learning models are trained on manual and ASR transcriptions of user utterances, using bag of words and n-grams feature generation approaches, and evaluated on ASR transcribed test set. Results show that models trained using ASR transcriptions perform better than algorithms trained on manual transcription. The impact of irregular distribution of dialogue acts on the accuracy of statistical models is also investigated, and a partial solution to this issue is shown using multimodal information as input.

Intelligent Virtual Agents are suitable means for interactive storytelling for children. The engagement level of child interaction with virtual agents is a challenging issue in this area. However, the characteristics of child-agent interaction received moderate to little attention in scientific studies whereas such knowledge may be crucial to design specific applications.

ABSTRACT Virtual agents are a real asset in collaborative virtual environment for training (CVET) as they can replace missing team members. Collaboration between such agents and users, however, is generally limited. We present here a whole integrated model of CVET focusing on the abstraction of the real or virtual nature of the actor to define a homogenous collaboration model. First, we define a new collaborative model of interaction. This model notably allows to abstract the real or virtual nature of a teammate. Moreover, we propose a new role exchange approach so that actors can swap their roles during training. The model also permits the use of physically based objects and characters animation to increase the realism of the world. Second, we design a new communicative agent model, which aims at improving collaboration with other actors using dialog to coordinate their actions and to share their knowledge. Finally, we evaluated the proposed model to estimate the resulting benefits for the users and we show that this is integrated in existing CVET applications. Copyright © 2014 John Wiley & Sons, Ltd.