Multiple pedagogical conversational agents to support learner-learner collaborative learning: Effects of splitting suggestion types

This study experimentally investigated the design of effective interactions using pedagogical conversational agents (PCAs) in a learner-learner collaborative learning activity. While dyads engaged in a concept explanation task (explaining the mechanism of computer processing), PCAs served as facilitators and provided metacognitive suggestions to better improve learning performance. Previous studies have shown that learners who received several types of suggestions from multiple PCAs were motivated to produce effective explanations; this study then further explored the effects of using multiple PCAs in different roles, providing different types of facilitation. It was predicted that by using two different PCAs to offer suggestions with a delay, learners may be able to process information more efficiently, for example by paying closer attention to each type of suggestion. To investigate this possibility, two types of facilitating content, namely provision of metacognitive suggestions and advice on effective coordination, were each implemented into two role-playing PCAs, named the “explanation adviser” and the “communication adviser” respectively. The results show that when learners used PCAs playing different roles and offering suggestions corresponding to these roles, learners generated explanations related to the suggestions and improved performance (efficacy of explanations) in several areas, including learning performance, for example better understanding the concept and becoming able to explain it using a greater range of technical words. This study shows empirically how multiple PCAs can be effectively designed to implement roles yielding different types of suggestions. The advantages of using such methods and implementing such functions of PCAs are further discussed.     

Empirical and modeling study of emotional state dynamics in social videogame paradigms

The objective of this work was to study the dynamics of human emotional states in the process of social interaction in a virtual environment. The previously developed for this purpose prototypes of the virtual actor (NPC) and its virtual environment simulator “Teleport” underwent significant re-design and modification. The experimental platform was re-implemented and used in experiments with college student participants, combining electromyography, emotion recognition in facial recordings and model-based game log analysis in a social videogame paradigm. Participants interacted with two virtual actors implemented based on the eBICA cognitive architecture (Samsonovich, 2013, 2018). Positive correlations were found between eBICA model predictions and participant affects extracted from their facial expressions and facial muscle activity. Affective dynamics of social phenomena, such as the establishment of partnership or an act of betrayal, were characterized and found consistent with the model predictions. Other findings include a gradually developing emotional reaction, possibly due to the integration of appraisals of game events. Overall, obtained results confirm the eBICA model, suggesting its further extension and refinement.     

ABC-EBDI: An affective framework for BDI agents

The aim of this work is to improve the modelling of intelligent agents that reproduce realistic human behavior. BDI frameworks have been successfully used in this context and have evolved in recent years into EBDI frameworks, in which affective aspects are considered. In this work, an affective EBDI framework named ABC-EBDI is presented. The proposal integrates a well-known psychotherapeutic model, the ABC model, combined with other affective theories, to support the modeling of the agents’ behavioral and affective responses in a unifying and realistic manner. The distinguishing feature of the proposed framework is the classification of the agent’s cognitive-affective process as either rational or irrational. This process will lead to functional emotions and adaptive conduct in the first case and dysfunctional emotions and maladaptive behaviors in the second. The framework models affect by taking into account emotions, mood and personality. It also models human conduct regarding not only actions, but also the way those actions are expressed. A prototype has been implemented based on a bad news scenario and a first evaluation with users has been carried out with promising results.     

An embodied model for sensorimotor grounding and grounding transfer: experiments with epigenetic robots

The grounding of symbols in computational models of linguistic abilities is one of the fundamental properties of psychologically plausible cognitive models. In this article, we present an embodied model for the grounding of language in action based on epigenetic robots. Epigenetic robotics is one of the new cognitive modeling approaches to modeling autonomous mental development. The robot model is based on an integrative vision of language in which linguistic abilities are strictly dependent on and grounded in other behaviors and skills. It uses simulated robots that learn through imitation the names of basic actions. Robots also learn higher order action concepts through the process of grounding transfer. The simulation demonstrates how new, higher order behavioral abilities can be autonomously built on previously grounded basic action categories following linguistic interaction with human users.     

Representing decision-makers using styles of behavior: An approach designed for group decision support systems

Supporting decision-making processes when the elements of a group are geographically dispersed and on a tight schedule is a complex task. Aiming to support decision-makers anytime and anywhere, Web-based group decision support systems have been studied. However, the limitations in the decision-makers’ interactions associated to this scenario bring new challenges. In this work, we propose a set of behavioral styles from which decision-makers’ intentions can be modelled into agents. The goal is that, besides having agents represent typical preferences of the decision-makers (towards alternatives and criteria), they can also represent their intentions. To do so, we conducted a survey with 64 participants in order to find homogeneous operating values so as to numerically define the proposed behavioral styles in four dimensions. In addition, we also propose a communication model that simulates the dialogues made by decision-makers in face-to-face meetings. We developed a prototype to simulate decision scenarios and found that agents are capable of acting according to the decision-makers’ intentions and fundamentally benefit from different possible behavioral styles, just as a face-to-face meeting benefits from the heterogeneity of its participants.     

Socially emotional brain-inspired cognitive architecture framework for artificial intelligence

Artificial Intelligence of the next generation needs to interact with users socially, convincing them in its ability to understand human minds, including emotions. For this to happen, an artificial emotional intelligence is needed, capable of adequate, believable behavior in social emotional interactions. Building on previous developments, the present work extends the general framework of emotional Biologically Inspired Cognitive Architecture (eBICA: Samsonovich, 2013, 2018), endowing it with fluents describing, in addition to appraisals, somatic markers, feelings, emotions, moods, emotional reactions and biases. Key building blocks that integrate them are moral schemas and semantic maps. The model describes interaction of three factors: plans and commitments, moral and ethical values, and somatic comfort. Learning in this framework includes self-organization of semantic maps that in turn may provide guidance for active humanlike learning. Implications for empirical studies and practical applications are discussed together with the expected impact.     

Soft constraints in interactive behavior: the case of ignoring perfect knowledge in-the-world for imperfect knowledge in-the-head

Constraints and dependencies among the elements of embodied cognition form patterns or microstrategies of interactive behavior. Hard constraints determine which microstrategies are possible. Soft constraints determine which of the possible microstrategies are most likely to be selected. When selection is non-deliberate or automatic the least effort microstrategy is chosen. In calculating the effort required to execute a microstrategy each of the three types of operations, memory retrieval, perception, and action, are given equal weight; that is, perceptual-motor activity does not have a privileged status with respect to memory. Soft constraints can work contrary to the designer’s intentions by making the access of perfect knowledge in-the-world more effortful than the access of imperfect knowledge in-the-head. These implications of soft constraints are tested in two experiments. In experiment 1 we varied the perceptual-motor effort of accessing knowledge in-the-world as well as the effort of retrieving items from memory. In experiment 2 we replicated one of the experiment 1 conditions to collect eye movement data. The results suggest that milliseconds matter. Soft constraints lead to a reliance on knowledge in-the-head even when the absolute difference in perceptual-motor versus memory retrieval effort is small, and even when relying on memory leads to a higher error rate and lower performance. We discuss the implications of soft constraints for routine interactive behavior, accounts of embodied cognition, and tool and interface design.