2025 Volume 37 Issue 3 Pages 662-670
In order for robots and virtual agents to interact naturally with humans, it is essential to build common ground with users. Few previous studies have investigated the process of building common ground in human interaction, and most of them are based on text chat. In this study, we focus on the modality of dialogue and social relationships among speakers and investigate the effects of these factors on the process of building common ground. Specifically, we collected and analyzed dialogues in which common ground was constructed among speakers under the conditions that the modality of the dialogues was audio or video and the social relationship was first meeting or friend. The results showed that the extension of modality and deep social relations accelerate the construction of common ground. Analysis of verbal behaviors also showed that deep social relationships increased the amount of speech required for task progression, and the extension of modality facilitated the transmission of empathic intentions, suggesting that reproducing dialogue acts between friends and nonverbal behaviors that convey empathic intentions are likely to be important when designing robots and virtual agents.
