Agents United

Beinema, Tessa; Davison, Daniel; Reidsma, Dennis; Baños, Oresti; Bruijnes, Merijn; Donval, Brice; Valero, Alvaro Fides; Heylen, Dirk; Hofs, Dennis; Huizing, Gerwin Harris; Kantharaju, Reshamashree B.; Klaassen, Randy; Kolkmeier, Jan; Konsolakis, Kostas; Pease, Alison; Pélachaud, Catherine; Simonetti, Donatella; Snaith, Mark; Traver, Vicente; Loon, Jorien van; Visser, Jacky; Weusthof, Marcel H.H.; Yunus, Fajrian; Hermens, Hermie; Akker, Harm op den

doi:10.1145/3472306.3478352

Cited by 10 publications

(4 citation statements)

References 28 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For our persuasive ECA, we implemented the customizable Unity Multipurpose Avatar 2 (UMA2) and seated the model within the user’s social space (ie, 2 m). We implemented the Agents United Dialogue Platform (ie, dialog manager, including generation of behavior markup language [BML]) [ 42 ], multimodal BML realizer Artificial Social Agents Platform (ASAP) [ 43 , 44 ], and related ASAP-Unity Bridge [ 45 ]. This includes Microsoft’s text-to-speech (TTS) engine (ie, Dutch Frank) with body language (ie, lip sync, gestures, gaze), partially scripted using the WOOL platform (WOOL Foundation; ie, gesture, gaze) [ 42 ], with gestures and posture animations using Unity’s built-in Mecanim system.…”

Section: Methodsmentioning

confidence: 99%

“…We implemented the Agents United Dialogue Platform (ie, dialog manager, including generation of behavior markup language [BML]) [ 42 ], multimodal BML realizer Artificial Social Agents Platform (ASAP) [ 43 , 44 ], and related ASAP-Unity Bridge [ 45 ]. This includes Microsoft’s text-to-speech (TTS) engine (ie, Dutch Frank) with body language (ie, lip sync, gestures, gaze), partially scripted using the WOOL platform (WOOL Foundation; ie, gesture, gaze) [ 42 ], with gestures and posture animations using Unity’s built-in Mecanim system. For user input, we integrated a dialog UI instead of speech recognition to avoid usability issues, given that the reliability of speech-to-text engines remains troublesome.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Development of an Alcohol Refusal Training in Immersive Virtual Reality for Patients With Mild to Borderline Intellectual Disability and Alcohol Use Disorder: Cocreation With Experts in Addiction Care

Langener¹,

Kolkmeier²,

VanDerNagel³

et al. 2023

JMIR Form Res

Self Cite

View full text Add to dashboard Cite

Background People with mild to borderline intellectual disability (MBID; IQ=50-85) are at risk for developing an alcohol use disorder (AUD). One factor contributing to this risk is sensitivity to peer pressure. Hence, tailored trainings are needed to practice alcohol refusal in impacted patients. Immersive virtual reality (IVR) appears promising to engage patients in dialogs with virtual humans, allowing to practice alcohol refusal realistically. However, requirements for such an IVR have not been studied for MBID/AUD. Objective This study aims to develop an IVR alcohol refusal training for patients with MBID and AUD. In this work, we cocreated our peer pressure simulation with experienced experts in addiction care. Methods We followed the Persuasive System Design (PSD) model to develop our IVR alcohol refusal training. With 5 experts from a Dutch addiction clinic for patients with MBID, we held 3 focus groups to design the virtual environment, persuasive virtual human(s), and persuasive dialog. Subsequently, we developed our initial IVR prototype and conducted another focus group to evaluate IVR and procedures for clinical usage, resulting in our final peer pressure simulation. Results Our experts described visiting a friend at home with multiple friends as the most relevant peer pressure situation in the clinical setting. Based on the identified requirements, we developed a social-housing apartment with multiple virtual friends present. Moreover, we embedded a virtual man with generic appearance to exert peer pressure using a persuasive dialog. Patients can respond to persuasive attempts by selecting (refusal) responses with varying degrees of risk for relapse in alcohol use. Our evaluation showed that experts value a realistic and interactable IVR. However, experts identified lacking persuasive design elements, such as paralanguage, for our virtual human. For clinical usage, a user-centered customization is needed to prevent adverse effects. Further, interventions should be therapist delivered to avoid try-and-error in patients with MBID. Lastly, we identified factors for immersion, as well as facilitators and barriers for IVR accessibility. Conclusions Our work establishes an initial PSD for IVR for alcohol refusal trainings in patients with MBID and AUD. With this, scholars can create comparable simulations by performing an analogous cocreation, replicate findings, and identify active PSD elements. For peer pressure, conveying emotional information in a virtual human’s voice (eg, paralanguage) seems vital. However, previous rapport building may be needed to ensure that virtual humans are perceived as cognitively capable entities. Future work should validate our PSD with patients and start developing IVR treatment protocols using interdisciplinary teams.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Development of an Alcohol Refusal Training in Immersive Virtual Reality for Patients With Mild to Borderline Intellectual Disability and Alcohol Use Disorder: Cocreation With Experts in Addiction Care

Langener¹,

Kolkmeier²,

VanDerNagel³

et al. 2023

JMIR Form Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…Relevant previous research projects in this field include Humaine (Online: ht tps://cordis.europa.eu/project/id/507422 (accessed on 30 June 2022)), which focused on emotional human-machine interaction and provided an extensive corpus of data on the forms emotion can take on during conversations [30], as well as Semaine (Online: https://cordis.europa.eu/project/id/211486 (accessed on 30 June 2022)), which explored the impact of nonverbal expressions such as head gestures [31] and laughter [32]. Technical artifacts resulting from these projects, such as GRETA [33] or the Agents United platform [34], help researchers and developers to setup their own multiagent applications. Furthermore, focusing more on the healthcare domain, the SimSensei system showed how CAs may be used as a tool to measure psychological distress in semi-structured interviews [35].…”

Section: Social Intelligence and Conversational Agentsmentioning

confidence: 99%

Perspectives on Socially Intelligent Conversational Agents

Brinkschulte

Schlögl

Monz

et al. 2022

MTI

View full text Add to dashboard Cite

The propagation of digital assistants is consistently progressing. Manifested by an uptake of ever more human-like conversational abilities, respective technologies are moving increasingly away from their role as voice-operated task enablers and becoming rather companion-like artifacts whose interaction style is rooted in anthropomorphic behavior. One of the required characteristics in this shift from a utilitarian tool to an emotional character is the adoption of social intelligence. Although past research has recognized this need, more multi-disciplinary investigations should be devoted to the exploration of relevant traits and their potential embedding in future agent technology. Aiming to lay a foundation for further developments, we report on the results of a Delphi study highlighting the respective opinions of 21 multi-disciplinary domain experts. Results exhibit 14 distinctive characteristics of social intelligence, grouped into different levels of consensus, maturity, and abstraction, which may be considered a relevant basis, assisting the definition and consequent development of socially intelligent conversational agents.

show abstract

“…Some of these applications may favor fully automated approaches, such as when only an input/output emotion label is needed [13], [14]. Other applications might need a set of intuitive parameters associated with values for each expression, in order to edit or analyze them [15], [16], [17], [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Emotion Expression in Human Body Posture and Movement: A Survey on Intelligible Motion Factors, Quantification and Validation

Mahfoudi

Meyer

Gaudin³

et al. 2023

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Many areas in computer science are facing the need to analyze, quantify and reproduce movements expressing emotions. This paper presents a systematic review of the intelligible factors involved in the expression of emotions in human movement and posture. We have gathered the works that have studied and tried to identify these factors by sweeping many disciplinary fields such as psychology, biomechanics, choreography, robotics and computer vision. These researches have each used their own definitions, units and emotions, which prevents a global and coherent vision. We propose a meta-analysis approach that cross-references and aggregates these researches in order to have a unified list of expressive factors quantified for each emotion. A calculation method is then proposed for each of the expressive factors and we extract them from an emotionally annotated animation dataset: Emilya. The comparison between the results of the meta-analysis and the Emilya analysis reveals high correlation rates, which validates the relevance of the quantified values obtained by both methodologies. The analysis of the results raises interesting perspectives for future research in affective computing.

show abstract

Agents United

Abstract: Figure 1: A group of ASAP (1, 3, 5) and GRETA (2, 4) agents in the same Unity environment. A user can participate in a multiparty group conversation by selecting a response from the menu on the right (in the same interface or on a separate device).

Cited by 10 publications

References 28 publications

Development of an Alcohol Refusal Training in Immersive Virtual Reality for Patients With Mild to Borderline Intellectual Disability and Alcohol Use Disorder: Cocreation With Experts in Addiction Care

Development of an Alcohol Refusal Training in Immersive Virtual Reality for Patients With Mild to Borderline Intellectual Disability and Alcohol Use Disorder: Cocreation With Experts in Addiction Care

Perspectives on Socially Intelligent Conversational Agents

Emotion Expression in Human Body Posture and Movement: A Survey on Intelligible Motion Factors, Quantification and Validation

Contact Info

Product

Resources

About