Virtual conversational agents

Human beings have adopted tools, pets, technology, especially computer science and Deep Learning (DL) in Virtual Intelligent Assistants (VIA). Digital technical assistance systems that predict the future in culture, business and politics are now in demand. The experience gained with Deep Learning (DL) is to be mapped to a model of a Virtual Intelligent Assistant (VIA) for social science, culture and economics. The Deep Learning (DL) model is based on an Artificial Neural Network (ANN) that contains artificial nodes (simplified nerve cells) and artificial neurons (simplified synapses). The special feature is that the artificial nodes (simplified nerve cells) are arranged in several hidden layers with autonomous filtering processes. Autonomous filters in the artificial nodes (simplified nerve cells) require rules that are static, i.e. time-invariant. For this purpose, the Logia of the Gospel of Thomas are proposed. It seems that the Gospel of Thomas summarizes insights and experiences from 80 thousand years of human history in 114 Logia. They are shown in outline points 1 to 114. Ultimately, the weight of the interaction determines that artificial neurons (simplified synapses) are represented in the model, as an entered statement at the output of the Artificial Neural Network (ANN) is to be understood. The boundaries between the machine, the individual and society continue to dissolve in the chaotic. It would be nice if world knowledge, as collected by the company Cyrorp, could be modelled. Instead of a model of world knowledge, Eva Soyah proposes the collection of Logia in subdivision points 1 to 114 and Permanent Truths from item 115.

L’era digitale ha indebolito la capacità di intrattenere una conversazione con sé stessi e con gli altri. Le più effimere forme di storytelling hanno preso il posto del dialogo a quattr’occhi e i piccoli momenti di noia sono avvertiti come un fastidio piuttosto che come un’occasione per l’introspezione. La tecnologia non può insegnare all’uomo a essere umano, ma può creare le condizioni per generare esperienze estremamente dinamiche, creative e arricchenti, che gli consentano di riacquisire le abilità di riflessione e di relazione. Per farlo, come in un processo di scaffolding, deve essere messa da parte al momento giusto. Questa proposta etica di disimpegno trova nella scuola, uno dei contesti di socializzazione nei quali si educa alla vita, un ambiente ideale per la sua realizzazione. Nella speranza di inaugurare una nuova fase della progettazione didattica, il contributo presenta un agente conversazionale il cui obiettivo è quello di abilitare forme di dialogo tra il docente e gli studenti.

Advances in the use of virtual affective agents for therapeutic purposes in mental health opened a research avenue to improve the way patients interpret other's behavior as helpful instead of menacing. Here, the authors propose an original paradigm based on affective computing and virtual reality technologies requiring the assessment of helping intentions as well as self-monitoring metacognition. Sixteen healthy subjects played a 38-turns card games with a virtual affective agent (MARC) during which they had to guess between two cards the one that would be color-matched with another card. Their guesses could be oriented by the agent's emotional displays. Three subjective ratings on a percentage analog scale were recorded after each trial: helpfulness, self- monitoring, and sympathy. Help recognition and self-monitoring metacognitive ratings raise the question of the importance to enhance both components in therapeutic situations within psychiatric populations. Overall, this ...

RÉSUMÉ. Cet article propose une architecture comportementale l’animation de personnages virtuels ayant des comportements sociaux et émotionnels. L’architecture proposée produit des actes de communication verbaux, paraverbaux et gestuels en prenant en compte les dimensions sociales et émotionnelles. L’objectif applicatif de cette approche est d’aboutir à un outil de simulation destiné à la rééducation de personnes cérébro-lésées en suivant un protocole dit des ‘neurones miroirs’. Dans la séance de rééducation virtuelle, le patient visualise une représentation virtuelle de son corps tout en étant guidé par un thérapeute virtuel qui le guide, le corrige et l’encourage. Notre objectif est d’aboutir à une sensation d’immersion chez le patient dans l’environnement virtuel via la reproduction des interactions
sociales et émotionnelles entre patient et thérapeute.

ABSTRACT. This article proposes a behavioural architecture for virtual characters who express social and emotional behaviours. The architecture proposed produces communication acts
for virtual characters (verbal, paraverbal and non-verbal activity) under the influence of a model of social and emotional interactions. The application of our work is a tool for the
simulation of a therapy for the rehabilitation of people with brain injuries caused by CVA (cerebral vascular accidents). In the virtual therapy the patient is represented by an avatar and an embodied conversational agent represents the therapist, who guides, corrects and encourages the patient. Our aim is to produce a feeling of immersion at the patient in the virtual environment through the reproduction of social and emotional interactions between
patient and therapist.

People tend to personify machines. Giving machines the ability to actually produce social information can help improve human-machine interactions. Embodied Conversational Agents (ECAs) are virtual software agents that can process and produce speech, facial expressions, gestures and eye gaze, enabling natural, multimodal, human-machine communication. On the one hand, the field of personality psychology provides insights into how we could describe and measure the virtual personality of ECAs. On the other hand, ECAs provide a method to systematically examine how different factors affect the perception of personality. This paper shows that standardized, validated personality questionnaires can be used to evaluate ECAs psychologically, and that state of the art ECAs can manipulate their perceived personality through appearance and behavior.

Advances in the use of virtual affective agents for therapeutic purposes in mental health opened a research avenue to improve the way patients interpret other's behavior as helpful instead of menacing. Here, the authors propose an original paradigm based on affective computing and virtual reality technologies requiring the assessment of helping intentions as well as self-monitoring metacognition. Sixteen healthy subjects played a 38-turns card games with a virtual affective agent (MARC) during which they had to guess between two cards the one that would be color-matched with another card. Their guesses could be oriented by the agent's emotional displays. Three subjective ratings on a percentage analog scale were recorded after each trial: helpfulness, self- monitoring, and sympathy. Help recognition and self-monitoring metacognitive ratings raise the question of the importance to enhance both components in therapeutic situations within psychiatric populations. Overall, this ...