The Role of Assertiveness in a Storytelling Game with Persuasive Robotic Non-Player Characters

Paradeda, Raul Benites; Ferreira, Maria José; Oliveira, Raquel; Martinho, Carlos; Paiva, Ana

doi:10.1145/3311350.3347162

Cited by 7 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous studies [29][30][31][32][33][34][35], persuasion strategies were individually used to assess their impact on people. Thus, the strategies that obtained interesting results were refined and adapted to perform combined in this study.…”

Section: Manipulationsmentioning

confidence: 99%

“…At these specific points, the persuasive agent applies the persuasion techniques to try to convince the participant to change the decision after s/he has informed the intention. The studies in [30][31][32][33], have contributed significantly with strategies that can improve the influence. The first study shows settings that can be used in an agent that makes people perceive it as an assertive agent which is a behaviour widely used in situations where influence is required.…”

Section: Manipulationsmentioning

confidence: 99%

See 1 more Smart Citation

Persuasion Strategies Using a Social Robot in an Interactive Storytelling Scenario

Paradeda

Martinho

Paiva

2020

Proceedings of the 8th International Conference on Human-Agent Interaction

Self Cite

View full text Add to dashboard Cite

The behaviour of a person in a given situation can be explained understanding his personality traits. In this sense, the identification of these traits can be a great value to achieve personalised social influence. Although there are several models of persuasion, few of them take into account the person's personality traits. For this reason, this work describes a persuasion study that takes into account a person's personality. We develop a storytelling decision-making scenario, where the participant receives influencing messages to follow a pattern of behaviour determined by a persuasive agent (an autonomous social robot with assertive behaviour). From the study, we find evidence that the model used within the proposed scenario managed to make participants more engaged in the activity. We found pieces of evidence that the levels of assertiveness of a person can influence their attitude and perception by an agent. Also, we identify that persuasion strategy which uses persuasive arguments are more efficient than strategies that have no arguments. Finally, our proposed persuasion strategies have achieved a good level of successful influence. CCS CONCEPTS • Computer systems organization → Robotic autonomy; • Human-centered computing → Empirical studies in HCI ; Laboratory experiments.

show abstract

Section: Manipulationsmentioning

confidence: 99%

Section: Manipulationsmentioning

confidence: 99%

Persuasion Strategies Using a Social Robot in an Interactive Storytelling Scenario

Paradeda

Martinho

Paiva

2020

Proceedings of the 8th International Conference on Human-Agent Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…Interaction between humans and agents/robots can greatly benefit from each other's ability to reason about the others' intentions-inferring what the other is trying to do and what its objectives are. In the human-robot interaction (HRI) literature, several works have explored the communication of intentions using speech [1,2], gaze [3,4], and movements [5,6]. In this work we address the problem of conveying intention through action, which is closely related to the aforementioned works that explore communication of intention through movement.…”

Section: Introductionmentioning

confidence: 99%

"Guess what I'm doing": Extending legibility to sequential decision tasks

Faria¹,

Melo²,

Paiva³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper we investigate the notion of legibility in sequential decision tasks under uncertainty. Previous works that extend legibility to scenarios beyond robot motion either focus on deterministic settings or are computationally too expensive. Our proposed approach, dubbed PoL-MDP, is able to handle uncertainty while remaining computationally tractable. We establish the advantages of our approach against state-of-the-art approaches in several simulated scenarios of different complexity. We also showcase the use of our legible policies as demonstrations for an inverse reinforcement learning agent, establishing their superiority against the commonly used demonstrations based on the optimal policy. Finally, we assess the legibility of our computed policies through a user study where people are asked to infer the goal of a mobile robot following a legible policy by observing its actions.

show abstract