2020/10/10 by Mengyao Li, Areen Alsaid, Li, Mengyao +7
Psychology · Social Sciences · #Human-Automation Interaction and Safety #Deception detection and forensic psychology #Ethics and Social Impacts of AI
paper · pdf · doi:10.48550/arxiv.2010.04885
The increasingly collaborative decision-making process between humans and agents demands a comprehensive, continuous, and unobtrusive measure of trust in agents. The gold standard format for measuring trust, a Likert-style survey, suffers from major limitations in dynamic human-agent interactions. We proposed a new approach to evaluate trust in a nondirective and relational conversation. The term nondirective refers to abstract word selections in open-ended prompts, which can probe respondents to freely describe their attitudes. The term relational refers to interactive conversations where respondents can clarify their responses in followup questions. We propose a systematic process for generating nondirective trust-based prompts by using text analysis from previously validated trust scales. This nondirective and relational approach provides a complementary trust measurement, which can unobtrusively elicit rich and dynamic information on situational trust throughout a human-agent interaction.