The article discusses the role of cognitive biases in decision-making and the need for automated detection of these biases. The research explores the use of conversational agents as a tool for measuring cognitive biases in different domains. Using existing experimental designs and tasks from the literature, the researchers developed a conversational agent capable of measuring biases. Initial experiments on framing and loss-aversion biases suggest the effectiveness of conversational agents in bias detection. The study underlines the importance of automated bias measurement in behavior change techniques and calls for more research in this area.
Publication date: 15 Jan 2024
Project Page: Not provided
Paper: https://arxiv.org/pdf/2401.06686
