Empathy Is All You Need: How a Conversational Agent Should Respond to Verbal Abuse

By Hyojin Chin, Lebogang Wame Molefi, Mun Yong Yi. 2020

104 citations recorded by the source corpus.

With the popularity of AI-infused systems, conversational agents (CAs) are becoming essential in diverse areas, offering new functionality and convenience, but simultaneously, suffering misuse and verbal abuse. We examine whether conversational agents' response styles under varying abuse types influence those emotions found to mitigate peoples' aggressive behaviors, involving three verbal abuse types (Insult, Threat, Swearing) and three response styles (Avoidance, Empathy, Counterattacking). Ninety-eight participants were assigned to one of the abuse type conditions, interacted with the three spoken (voice-based) CAs in turn, and reported their feelings about guiltiness, anger, and shame after each session. The results show that the agent's response style has a significant effect on user emotions. Participants were less angry and more guilty with the empathy agent than the other two agents. Furthermore, we investigated the current status of commercial CAs' responses to verbal abuse. Our study findings have direct implications for the design of conversational agents.

Subfields: Artificial Intelligence, Social Psychology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Social Psychology

In Natural Language Processing

Citations in the corpus

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “Chin & Yi (2019); Chin et al. (2020) assess the reported effects of different strategies on experiment participants who have been assigned the roles of threatening, insulting, and swearing at conversational agents.”
Recipes for Safety in Open-domain Chatbots (2020, background): “Chin and Yi (2019); Chin et al. (2020) compare three ways a conversational agent can respond to abusive messages: avoidance that attempts to disengage from the subject ("Sorry, I didn’t catch that.")”
Bot-Adversarial Dialogue for Safe Conversational Agents (2021, background): “” Previous works have compared response strategies, including avoidance, joking or polite deflection, non-committal answers, play-along, confrontation, apologetic responding, empathizing, and counter-attacking responses (Curry and Rieser, 2019; Chin and Yi, 2019; Chin et al., 2020; Paranjape et al.,”
Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations (2020, methodology): “We also implemented the strategy COUNTER+PROMPT , inspired by Brahnam (2005), which directly confronts the user before changing topic, and EMPATHETIC+PROMPT , inspired by Chin et al. (2020), which empathizes with the user before changing topic.”
SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures (2021, background): “Chin and Yi (2019); Chin et al. (2020) look at how different response strategies (disengaging, apologizing, or counter-attacking) can change how conversational models are rated and how many negative responses they elicit.”
Assessing Political Prudence of Open-domain Chatbots (2021, methodology): “Besides measurement and mitigation methods, Curry and Rieser (2019); Chin and Yi (2019); Chin et al. (2020) have studied different response methods (empathy, counter-attack, question etc.) to adversarial attacks from users.”