Stupid computer! Abuse and social identities

43 citations recorded by the source corpus.

How researchers see this paper

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

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “Non-adversarial unsafe setting: Past research suggests that one in ten human-bot conversations may contain abusive behavior on the part of the human (De Angeli & Carpenter, 2005; De Angeli & Brahnam, 2008).”
Recipes for Safety in Open-domain Chatbots (2020, background): “Other past studies (De Angeli and Carpenter, 2005; De Angeli and Brahnam, 2008) suggest that one in ten human-bot conversations may contain instances of the human demonstrating unprovoked abusive behavior towards the chatbot.”
Bot-Adversarial Dialogue for Safe Conversational Agents (2021, background): “De Angeli and Carpenter (2005); De Angeli and Brahnam (2008) suggest that one in ten human-bot conversations may contain instances of the human demonstrating unprovoked abusive behavior towards the chatbot.”
SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022, background): “This can for example include abusive user behavior, which according to past research affects one in ten human-bot conversations (De Angeli and Carpenter, 2005; De Angeli and Brahnam, 2008).”
A Crowd-based Evaluation of Abuse Response Strategies in Conversational Agents (2019, background): “, 2018), and how to handle verbal abuse from the user’s side (Cercas Curry and Rieser, 2018; Angeli and Brahnam, 2008; Angeli and Carpenter, 2006; Brahnam, 2005).”