Paper Number
ECIS2026-1303
Paper Type
CRP
Abstract
This paper investigates the role of anthropomorphic design in Large Language Models (LLMs), particularly in the context of lifestyle behavior change coaching. This study examines how specific verbal social cues – namely small talk and self-referential social cues – affect user perceptions of anthropomorphism, trust, and eeriness. Findings from a 2x2 experiment show that self-referential social cues enhance perceptions of anthropomorphism, which in turn positively influence user trust. At the same time, the combined use self-referential social cues and small talk can have adverse effects, suggesting a potential uncanny valley effect in text-based interactions. These results highlight the nuanced role of verbal social cues in shaping user perceptions and provide insights for designing more effective and trustworthy LLM-based coaching systems.
Recommended Citation
Meywirth, Sophia, "The Role Of Self-Referential Social Cues and Small Talk In Large Language Model-Based Health Coaching: Enhancing Anthropomorphism and User Trust" (2026). ECIS 2026 Proceedings. 5.
https://aisel.aisnet.org/ecis2026/ai_anthro/ai_anthro/5
The Role Of Self-Referential Social Cues and Small Talk In Large Language Model-Based Health Coaching: Enhancing Anthropomorphism and User Trust
This paper investigates the role of anthropomorphic design in Large Language Models (LLMs), particularly in the context of lifestyle behavior change coaching. This study examines how specific verbal social cues – namely small talk and self-referential social cues – affect user perceptions of anthropomorphism, trust, and eeriness. Findings from a 2x2 experiment show that self-referential social cues enhance perceptions of anthropomorphism, which in turn positively influence user trust. At the same time, the combined use self-referential social cues and small talk can have adverse effects, suggesting a potential uncanny valley effect in text-based interactions. These results highlight the nuanced role of verbal social cues in shaping user perceptions and provide insights for designing more effective and trustworthy LLM-based coaching systems.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.