Rui Prada

AAMAS Conference 2024 Conference Paper

Towards Sustainable Human-Agent Teams: A Framework for Understanding Human-Agent Team Dynamics

• Rui Prada
• Astrid C. Homan
• Gerben A. van Kleef

Human-agent teamwork is a promising research stream with great potential to impact society. Research on collaborative AI and humanagent interaction has tackled the problem from several perspectives, but we argue that a focus on teams as a unit and a model for humanagent team dynamics is missing. Such a focus is particularly relevant if we aim at involving agents as active team members and at building sustainable teams over time. A team perspective on human-agent collaboration requires new models that pose challenges for AI and humans alike. AI needs new models to build an understanding of team level variables, such as team structure and cohesion, to be able to monitor the team and act on the team beyond performing the task. Humans, in turn, need to be able to incorporate agents as team members in their mental models of teamwork and integrate them into team processes. Such human-agent team dynamics models should be built taking into account four different levels: individual, interpersonal, team, and organisational. We believe that to fulfill this vision we need to bring together the different fields of AI and social sciences.

AAMAS Conference 2022 Conference Paper

Behavior vs Appearance: What Type of Adaptations are More Socially Motivated?

• Diogo Rato
• Marta Couto
• Rui Prada

For autonomous agents to successfully perform in open hybrid scenarios (with people and agents), they need to adapt to different social contexts. Simultaneously, the people involved must understand the observed changes in the agents, particularly to identify the social motivations for such behavior. In this paper, we report an experimental study conducted to assess if an agent’s behavioral changes (gait), are perceived as more socially motivated than its appearance adaptations (color). Furthermore, we explore if other agents’ presence and behavior affect the attribution of motivations. Our findings suggest that external observers identify agents’ appearance adaptations as more socially and spatially motivated than behavioral changes. Furthermore, the agents’ awareness is rated higher when the agents adjust their physical characteristics compared to behavioral adaptations.

AAMAS Conference 2019 Conference Paper

An Accessible Toolkit for the Creation of Socio-EmotionalAgents

• Manuel Guimarães
• Samuel Mascarenhas
• Rui Prada
• Pedro A. Santos
• João Dias

FAtiMA Toolkit is a collection of open-source tools that is designed to facilitate the creation and use of cognitive agents with socioemotional skills. The toolkit was developed with a focus on accessibility so it could be used by both researchers and game developers. It provides a computational model of emotions that is based on the OCC appraisal theory as well as an explicit dialogue structure that is familiar to game developers while maintaining the flexibility of an approach based on autonomous agents. Among various use cases, the toolkit has been successfully applied by an external game studio in their development of two serious games.

AAMAS Conference 2019 Conference Paper

For The Record - A Public Goods Game For Exploring Human-Robot Collaboration

• Filipa Correia
• Samuel Mascarenhas
• Samuel Gomes
• Silvia Tulli
• Fernando P. Santos
• Francisco C. Santos
• Rui Prada
• Francisco S. Melo

For The Record is a digital game that involves a social dilemma between a mixed team of humans and agents. Inspired by the standard public goods games, the collective goal is accessible to all team members, independently of their individual contributions. As a result, each player faces in each round the decision between cooperating with the team and defecting to obtain an individual benefit. The digital game itself allows exploring the complexity of human cooperation when teaming with agents. Moreover, playing it on a touch screen creates an additional opportunity to explore these interactions when teaming with social robots.

AAMAS Conference 2019 Conference Paper

Social Power in Human-Robot Interaction: Towards More Persuasive Robots

• Mojgan Hashemian
• Ana Paiva
• Samuel Mascarenhas
• Pedro A. Santos
• Rui Prada

Social power is defined as one’s ability to influence another to do something which s/he would not do without the presence of such power. Different theories classify alternative ways to achieve social power, such as providing a reward, using coercion, or acting as an expert. In this work, we explored two types of persuasive strategies that are based on social power (specifically Reward and Expertise) and created two social robots that would employ such strategies. To examine the effectiveness of these strategies we performed a user study with 51 participants using two social robots in an adversarial setting in which both robots try to persuade the user on a concrete choice. The results show that even though each of the strategies caused the robots to be perceived differently in terms of their competence and warmth, both were similarly persuasive.

AAMAS Conference 2017 Conference Paper

Affect of Robot's Competencies on Children's Perception

• Shruti Chandra
• Raul Paradeda
• Hang Yin
• Pierre Dillenbourg
• Rui Prada
• Ana Paiva

The focus of the research described in this paper is to explore children’s perception of a social robot’s learning abilities and behavior in an educational context. With this purpose, we conducted a long-term study with children in a school by adopting the learning-by-teaching learning method. The scenario involves a ”learner-agent” (a robot) which seeks help from a child (a teacher) in correcting the shapes of a few letters it writes. Two versions of the robot were built: one where it learns and another where it does not improve over time. The results of the study suggest that children’s social relationship with the robot was not affected by the learning abilities of the agent.

AAMAS Conference 2017 Conference Paper

FIDES: How Emotions and Small Talks May Influence Trust in an Embodied vs. Non-embodied Robot

• Raul Paradeda
• Mojgan Hashemian
• Carla Guerra
• Rui Prada
• Joã o Dias
• Ana Paiva

Trust is known as a complex social-emotional concept and its formation is highly affected by non-verbal behavior. Social robots, as any other social entities, are supposed to maintain a level of trustworthiness during their interactions with humans. In this sense, we have examined the influence of a set of factors, including emotional representation, performing small talk and embodiment, on the way people infer trustworthiness of a robot. To examine these factors, we have performed different experiments using two robots, NAO and Emys, with and without physical embodiment respectively. To measure trust levels, we assumed two different metrics, a trust questionnaire and the amount of donations the participants would make. The results suggest that these factors influence significantly the level of trust. As, people tend to trust on Emys significantly differently depending on its facial expressions and making or not making small talk, and, people tend to donate differently to NAO when it is performing different emotional gestures and making or not making small talk. Furthermore, the trust levels were significantly different regarding the embodiment, comparing the experiments with Emys versus with NAO.

AAMAS Conference 2017 Conference Paper

Strategically Misleading the User: Building a Deceptive Virtual Suspect

• Diogo Rato
• Brian Ravenet
• Rui Prada
• Ana Paiva

Humans lie every day, from the least harmful lies to the most impactful ones. Therefore, in an attempt to design virtual agents endowed with advanced decision-making abilities, researchers not only focused their effort in designing cooperative and truthful agents but also deceptive and lying ones. In this paper we propose a model capable of engaging an agent in an uncooperative misleading dialogue with a user. This model gives to an agent the ability to reason about its knowledge and then autonomously adjust the story it tells depending on what its interlocutors might know and on how sensitive it considers the conversation topic to be. Such a model allows a story’s author to focus on the main narrative, letting the model handle the generation of alternatives. We implemented the model in an agent called the Deceptive Virtual Suspect and conducted some preliminary experiments using an Interrogation Game.

AIJ Journal 2016 Journal Article

Integrating social power into the decision-making of cognitive agents

• Gonçalo Pereira
• Rui Prada
• Pedro A. Santos

Social power is a pervasive feature with acknowledged impact in a multitude of social processes. However, despite its importance, common approaches to social power interactions in multi-agent systems are rather simplistic and lack a full comprehensive view of the processes involved. In this work, we integrated a comprehensive model of social power dynamics into a cognitive agent architecture based on an operationalization of different bases of social power inspired by theoretical background research in social psychology. The model was implemented in an agent framework that was subsequently used to generate the behavior of virtual characters in an interactive virtual environment. We performed a user study to assess users' perceptions of the agents and found evidence supporting both the social power capabilities provided by the model and their value for the creation of believable and interesting scenarios. We expect that these advances and the collected evidence can be used to support the development of agent systems with an enriched capacity for social agent simulation.

AAMAS Conference 2016 Conference Paper

Modeling Culture in Intelligent Virtual Agents - From Theory to Implementation (JAAMAS Extended Abstract)

• Samuel Mascarenhas
• Nick Degens
• Ana Paiva
• Rui Prada
• Gert Jan Hofstede
• Adrie Beulens
• RUTH AYLETT

AAAI Conference 2014 Conference Paper

Accurate Household Occupant Behavior Modeling Based on Data Mining Techniques

• Márcia Baptista
• Anjie Fang
• Helmut Prendinger
• Rui Prada
• Yohei Yamaguchi

An important requirement of household energy simulation models is their accuracy in estimating energy demand and its fluctuations. Occupant behavior has a major impact upon energy demand. However, Markov chains, the traditional approach to model occupant behavior, (1) has limitations in accurately capturing the coordinated behavior of occupants and (2) is prone to over-fitting. To address these issues, we propose a novel approach that relies on a combination of data mining techniques. The core idea of our model is to determine the behavior of occupants based on nearest neighbor comparison over a database of sample data. Importantly, the model takes into account features related to the coordination of occupants’ activities. We use a customized distance function suited for mixed categorical and numerical data. Further, association rule learning allows us to capture the coordination between occupants. Using real data from four households in Japan we are able to show that our model outperforms the traditional Markov chain model with respect to occupant coordination and generalization of behavior patterns.

AAMAS Conference 2013 Conference Paper

"Can I ask you a favour? " - A Relational Model of Socio-Cultural Behaviour

• Samuel Mascarenhas
• Rui Prada
• Ana Paiva
• Nick Degens
• Gert Jan Hofstede

In this paper we provide an overall description of a model of social behaviour that allows a flexible parametrisation of cultural expectations. These expectations are associated to how people perceive and treat others from a socio-relational perspective.

AAMAS Conference 2013 Conference Paper

Bases of Social Power for Agents

• Gonçalo Pereira
• Rui Prada
• Pedro A. Santos

One of the most pervasive concepts in human interactions is social power since many social situations entail disputes of social power. These disputes are power games and range from simple personal reasoning to the exercise of specific power strategies, which enhance or assert one’s power. Recognizing the importance of such interactions and how they can enhance autonomous agents’ socially intelligent behaviors, we present a conceptual framework integrating the different bases of power as social forces that can underlie an agent’s deliberative decision process. This work establishes a theoretical basis for social intelligent agents capable of both being aware of and manipulating social power.

AAMAS Conference 2013 Conference Paper

You Are Who You Hang Out With: Agents With Dynamic Identity

• Joana Dimas
• Rui Prada

The presence of others as well as several other social context’s factors have an affect on the way someone is going to perceive oneself. Whether as unique and distinctive individual, or as part of a group with shared interests among its members, the perception of group membership is going to determine if one’s behaviour is going to be influenced by one’s personal identity or social identity. When a social identity is salient, people tend to cooperate more with members of their group, even when the group’s goals differ from their own personal goals. In this paper, we introduce Dynamic Identity Model for Agents that provides agents with an adaptive identity and behaviour that is adjustable to the social context.

AAMAS Conference 2012 Conference Paper

The Role of Social Identity, Rationality and Anticipation in Believable Agents

• Rui Prada
• Guilherme Raimundo
• M
• aacute; rcia Baptista
• Joana Dimas
• Pedro A. Santos
• Carlos Martinho
• Jorge Pe

Agents that interact in complex social situations need to take the social context in consideration in order to perform believably. We argue that social identity is an important factor; therefore, agents should incorporate social identity theory in their behaviour, which implies the ability to categorize others (and themselves) into social groups. In addition, social situations often present social dilemmas with expected rational choices. Social identity may influence the agent to deviate from the rational choice. However, in some situations the rational choice may be the expected, and believable, behaviour. In fact, we argue that finding the dynamics between the social bias induced by social identity and the rational motivation is one of the challenges of building believable agents. In all this, anticipation takes an important role, as it is important to understand the others to cope well with a social situation.

ECAI Conference 2010 Conference Paper

Introducing Personality into Team Dynamics

• Rui Prada
• João Camilo
• Maria Augusta Silveira Netto Nunes

If autonomous agents interact with people, they should achieve the suspension of disbelief in order to offer a good interaction experience to users. To achieve this it is important that the agents' behaviours are consistent with a given personality since people have a tendency to attribute personality to interactive artifacts. The concept of personality is also useful to create diversity in multi-agent simulations even if users do not directly engage in the interactions, for example, to explore different strategies in simulated societies. This paper presents a computational model of personality based on the Five Factor Model of personality for the behaviour of social autonomous agents that interact in teamwork scenarios.

AIJ Journal 2009 Journal Article

Teaming up humans with autonomous synthetic characters

• Rui Prada
• Ana Paiva

Autonomous synthetic characters have the potential to promote the social engagement of users in virtual environments, enhancing their interaction experience. In computer games, for example, poor interaction with game characters can drastically detract from the gaming experience, making the design of autonomous synthetic characters an important issue. In particular, in Role Playing Games (RPGs), for example, users and autonomous characters often perform in a group. Usually, the role of such characters is very limited since they lack the social skills to perform coherently in group scenarios. The goal of the work presented here is to endow autonomous synthetic characters with social skills that allow them to perform in groups with human members. However, to successfully achieve this, it is not enough to assure that the characters behave in a coherent manner from an individual perspective or that they are able to perform the group task optimally. It is also necessary that the autonomous characters exhibit behaviours that are coherent with the group's composition, context and structure. For this reason, we have developed a model to support group dynamics of autonomous synthetic characters (SGD model) inspired by theories developed in human social psychological sciences. This model defines the knowledge that each individual should build about the others and the group, and how this knowledge drives their interactions. The model was used in a collaborative computer game that was tested with users. The results showed that the model had a positive effect on the users' social engagement, namely, on their trust and identification with the group.

AAMAS Conference 2005 Conference Paper

Believable Groups of Synthetic Characters

• Rui Prada
• Ana Paiva