Does the Appearance of Autonomous Conversational Robots Affect User Spoken Behaviors in Real-World Conference Interactions?
This research addresses the problem of optimizing robot design for better human-robot communication, particularly in conversational settings, but it is incremental as it builds on existing theories like cognitive load and Communication Accommodation Theory.
The study investigated how robot appearance affects users' spoken behavior in real-world conference interactions, finding that participants produced fewer disfluencies and used more complex syntax with a human-like android compared to a less anthropomorphic humanoid, with moderate effect sizes and a classification model achieving an F1-score of 71.60%.
We investigate the impact of robot appearance on users' spoken behavior during real-world interactions by comparing a human-like android, ERICA, with a less anthropomorphic humanoid, TELECO. Analyzing data from 42 participants at SIGDIAL 2024, we extracted linguistic features such as disfluencies and syntactic complexity from conversation transcripts. The results showed moderate effect sizes, suggesting that participants produced fewer disfluencies and employed more complex syntax when interacting with ERICA. Further analysis involving training classification models like Naïve Bayes, which achieved an F1-score of 71.60\%, and conducting feature importance analysis, highlighted the significant role of disfluencies and syntactic complexity in interactions with robots of varying human-like appearances. Discussing these findings within the frameworks of cognitive load and Communication Accommodation Theory, we conclude that designing robots to elicit more structured and fluent user speech can enhance their communicative alignment with humans.