Managing an Agent's Self-Presentational Strategies During an Interaction.

Beatrice Biancardi,Catherine Pelachaud,Maurizio Mancini,Paul Lerner

doi:10.3389/frobt.2019.00093

Abstract

In this paper we present a computational model for managing the impressions of warmth and competence (the two fundamental dimensions of social cognition) of an Embodied Conversational Agent (ECA) while interacting with a human. The ECA can choose among four different self-presentational strategies eliciting different impressions of warmth and/or competence in the user, through its verbal and non-verbal behavior. The choice of the non-verbal behaviors displayed by the ECA relies on our previous studies. In our first study, we annotated videos of human-human natural interactions of an expert on a given topic talking to a novice, in order to find associations between the warmth and competence elicited by the expert's non-verbal behaviors (such as type of gestures, arms rest poses, smiling). In a second study, we investigated whether the most relevant non-verbal cues found in the previous study were perceived in the same way when displayed by an ECA. The computational learning model presented in this paper aims to learn in real-time the best strategy (i.e., the degree of warmth and/or competence to display) for the ECA, that is, the one which maximizes user's engagement during the interaction. We also present an evaluation study, aiming to investigate our model in a real context. In the experimental scenario, the ECA plays the role of a museum guide introducing an exposition about video games. We collected data from 75 visitors of a science museum. The ECA was displayed in human dimension on a big screen in front of the participant, with a Kinect on the top. During the interaction, the ECA could adopt one of 4 self-presentational strategies during the whole interaction, or it could select one strategy randomly for each speaking turn, or it could use a reinforcement learning algorithm to choose the strategy having the highest reward (i.e., user's engagement) after each speaking turn.

Highlights

AND MOTIVATIONDuring the last decades, anthropomorphic interfaces, such as humanoid robots and virtual characters, have been increasingly deployed in several roles, such as pedagogical assistants, companion, trainers
User’s perception of agent’s warmth (w) and competence (c): we presented a list of adjectives referring to Warmth and Competence (W&C) and asked participants to indicate their agreement on a 5-points Likert scale (1 = “I completely disagree,” 5 = “I completely agree”) about how precisely each adjective described the character
Alice was rated as colder when she adopted INTIM strategy, compared to the other conditions. This supports the thesis of the primacy of warmth dimension (Wojciszke and Abele, 2008, see section 2), and it is in line with the positive-negative asymmetry effect described by Peeters and Czapinski (1990), who argues that negative information has generally a higher impact in person perception than positive information

Summary

Introduction

AND MOTIVATIONDuring the last decades, anthropomorphic interfaces, such as humanoid robots and virtual characters, have been increasingly deployed in several roles, such as pedagogical assistants, companion, trainers. Virtual agents ought to be endowed with the capability of maintaining engaging interactions with users (Sidner and Dzikovska, 2005) This would make it easier for a virtual guide to transmit information, would ensure change behavior for a virtual coach, would create rapport with a virtual companion. People are quite accurate at forming this kind of impressions, by collecting and integrating information from others’ appearance and behaviors This process, defined by Goffman and his colleagues as impression formation, is naturally coupled with impression management, that is, the attempt to control the impressions that one gives to the others (Goffman et al, 1978). Several authors investigated the fundamental dimensions of social cognition, that is, those characteristics of the others that are processed from the initial moments of an interaction These authors converged, even if adopting different terminology, to two main dimensions (Abele and Wojciszke, 2013). In the current work we refer to competence as cognitive competence (knowledge, abstract intelligence and experience)

Objectives

Results

Conclusion