Empathy in Virtual Agents and Robots

Abstract

This article surveys the area of computational empathy, analysing different ways by which artificial agents can simulate and trigger empathy in their interactions with humans. Empathic agents can be seen as agents that have the capacity to place themselves into the position of a user’s or another agent’s emotional situation and respond appropriately. We also survey artificial agents that, by their design and behaviour, can lead users to respond emotionally as if they were experiencing the agent’s situation. In the course of this survey, we present the research conducted to date on empathic agents in light of the principles and mechanisms of empathy found in humans. We end by discussing some of the main challenges that this exciting area will be facing in the future.

How Players Speak to an Intelligent Game Character Using Natural Language Messages

“…The way in which a subset of players anthropomorphised help_bot is consistent with past studies of conversational interaction (Luger and Sellen 2016) and empathic agents (Paiva et al 2017), and representative of a wider effect in human-computer interaction: the tendency for people to respond to computers as though they are human, which Reeves and Nass have dubbed the "Media Equation" (1996). Nass and Moon argue that users "mindlessly" (2000, 82) apply social rules and expectations to computers, and Nass and Brave (2005) suggest that this effect is particularly strong for interactions involving speech.…”

Robots Like Me: Challenges and Ethical Issues in Aged Care

“…Thirty years later, there are robots developed for the daily care activities of persons, like lifting, bathing or feeding, including ethical reflection from the care ethics tradition (Van Wynsberghe, 2013 ). There are also robots or artificial agents that appear able to engage in conversation with people and keep track of personal information (Mattar and Wachsmuth, 2014 ; Ng et al, 2017 ) or that can simulate and trigger empathy in their interactions with humans (Paiva et al, 2017 ).…”

Validating Automated Sentiment Analysis of Online Cognitive Behavioral Therapy Patient Texts: An Exploratory Study

“…Examples are a good therapeutic alliance, positive expectancy effects of both the patient and the coach, therapeutic competence of the supportive human, and the content of written feedback (Mohr et al, 2011; Schueller et al, 2017; Mol et al, 2018). An important element in many of these factors is “empathy”, i.e., perceiving and understanding others’ affective states and acting accordingly (Paiva et al, 2017), which can contribute to a good therapeutic relationship between a supportive human and patient, both in face-to-face (Keijsers et al, 2000), and online settings (Mohr et al, 2011). Similar to human-human interaction, empathy simulated by an ECA can contribute to the bond between the user and ECA, as research has shown, for example, that empathic ECAs are seen as more trustworthy, likeable, and caring (Brave et al, 2005), and can build and sustain long-term relationships with users (Bickmore and Picard, 2005).…”