Should an Agent Be Ignoring It?: A Study of Verbal Abuse Types and Conversational Agents' Response Styles

By Hyojin Chin, Mun Yong Yi. 2019

39 citations recorded by the source corpus.

Verbal abuse is a hostile form of communication ill-intended to harm the other person. With a plethora of AI solutions around, the other person being targeted may be a conversational agent. In this study, involving 3 verbal abuse types (Insult, Threat, Swearing) and 3 response styles (Avoidance, Empathy, Counterattacking), we examine whether a conversational agent's response style under varying abuse types influences those emotions found to mitigate people's aggressive behaviors. Sixty-four participants, assigned to one of the abuse type conditions, interacted with the three conversational agents in turn and reported their feelings about guiltiness, anger, and shame after each session. Our study results show that, regardless of the abuse type, the agent's response style has a significant effect on user emotions. Participants were less angry and more guilty with the empathetic agent than the other two agents. Our study findings have direct implications for the design of conversational agents.

Subfields: Social Psychology, Sociology and Political Science, 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 Social Psychology

In Sociology and Political Science

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.,”
ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI (2021, background): “Following this report, several recent works have investigated possible abuse mitigation strategies (Cercas Curry and Rieser, 2018, 2019; Chin and Yi, 2019; Ma et al., 2019).”
Empathy Is All You Need: How a Conversational Agent Should Respond to Verbal Abuse (2020, methodology): “Moreover, most prior research examined text-based interactions [10, 11, 18, 22].”
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.”
A Crowd-based Evaluation of Abuse Response Strategies in Conversational Agents (2019, background): “Chin and Yi (2019) make a first step into this direction by investigating different response styles (Avoidance, Empathy, Counterattacking) to verbal abuse, and recording the user’s emotional reaction – hoping that eliciting certain emotions, such as guilt, will”