Talking to Bots: Symbiotic Agency and the Case of Tay

By Gina Neff. 2016

349 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.

In Natural Language Processing

Citations in the corpus

Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, background): “While engagingness is necessary for people to be willing to talk to a conversational agent, it is not sufficient: Tay (Neff and Nagy, 2016; Miller, Wolf, and Grodzinsky, 2017) is an example of agent that might have been engaging, but in a way that required its removal.”
How Should My Chatbot Interact? A Survey on Social Characteristics in Human–Chatbot Interaction Design (2019, background): “The lack of this ability may lead to cases such as Tay, the Microsoft’s Twitter chatbot that became racist, sexist, and harasser in a few hours [Neff and Nagy 2016].”
Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design (2020, background): “Tay, the Twitter bot, provides an extreme example [36].”
Value Alignment or Misalignment - What Will Keep Systems Accountable? (2017, background): “…and consequent damage in the social sphere, when social chatbots are released “in the wild” and its “learning preferences” are all too easy to corrupt and degrade (see Microsoft’s recent Twitter agent Tay, which within a short time sounded like a fervent Nazi supporter (Neff and Nagy 2016)).”
How to Design AI for Social Good: Seven Essential Factors (2020, background): “…in the real—and frequently vicious—world of social media, however, the bot’s ability to adapt constantly its “conceptual understanding” became an unfortunate bug, as Tay “learned” and regurgitated offensive language and unethical associations between concepts from other users (Neff and Nagy 2016).”
Towards a Standard for Identifying and Managing Bias in Artificial Intelligence (2022, background): “The set of harms that can arise from the use of NLP however has become a recent concern in the area of trustworthy AI [81, 91, 158, 168, 169].”
ORES (2019, background): “Any approach that seeks to expand access to a potentially harmful technology should also be mindful about unintended uses and abuses, as adversaries and harms in the content moderation space are numerous [70, 81, 108].”