Conversational AI is increasingly positioned as a teammate rather than a tool, yet little is known about how its presence reshapes communication among human teammates. We examined sociocognitive communication dynamics in a team decision-making task using Group Communication Analysis (GCA), surveys, and lexical analyses. Sixteen teams of two students and an AI teammate and 17 all-human teams of three completed a high-stakes moral-dilemma task. Mixed-effects models showed that the AI participated more and was more internally cohesive but contributed less new and less dense content than students. Compared with controls, students on AI-inclusive teams showed lower participation, responsivity, and social impact and reported lower belonging, status, and connection. Event-locked models found no condition differences in trajectories of socioemotional content or student-student linguistic style matching. These findings suggest a social cost to students' experienced team membership and relational integration in AI-inclusive teams, although the temporal analyses do not establish when this cost emerged. We discuss implications for future research in voice-based and longitudinal settings.

翻译：暂无翻译