Speaking or Writing : Do Response Times Influence Anthropomorphism Differently for ADHD and Neurotypical Users in a Mental Health Chatbot?
Holmberg, Linus ; Sikström, Sverker LU
and Riveiro, Maria
(2026)
13th International Conference on Human-Agent Interaction, HAI 2025
In HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction
p.50-57
- Abstract
The emergence of large language models (LLMs) has made it easier than ever to create chatbots capable of generating human-like responses to user inputs. Moreover, improvements in text-to-speech and speech-to-text make it possible to converse with these systems, not just in text but also through speech. These improvements have led to an increase in chatbot applications across various contexts, such as customer service and healthcare. This study examined the tendency to anthropomorphize chatbots in a mental health assessment context. Participants were randomized to interact with the chatbot via a text-based or voice-based interface. Neurotypical individuals (n = 62) and individuals with ADHD (n = 45) were recruited. The analysis revealed... (More)
The emergence of large language models (LLMs) has made it easier than ever to create chatbots capable of generating human-like responses to user inputs. Moreover, improvements in text-to-speech and speech-to-text make it possible to converse with these systems, not just in text but also through speech. These improvements have led to an increase in chatbot applications across various contexts, such as customer service and healthcare. This study examined the tendency to anthropomorphize chatbots in a mental health assessment context. Participants were randomized to interact with the chatbot via a text-based or voice-based interface. Neurotypical individuals (n = 62) and individuals with ADHD (n = 45) were recruited. The analysis revealed a significant Modality × Neurotype interaction, indicating that modality affected the groups differently. Follow-up simple-effects analyses suggested that ADHD participants tended to anthropomorphize less in the voice condition than the text condition, whereas neurotypical participants showed no reliable difference between modalities. Because response latency differed across conditions, causal attributions to modality alone cannot be made. We discuss response timing as a likely driver and implications for inclusive chatbot design.
(Less)
- author
- Holmberg, Linus
; Sikström, Sverker
LU
and Riveiro, Maria
- organization
- publishing date
- 2026-01-02
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- ADHD, Anthropomorphism, Chatbot, Human-Computer Interaction, Mental Health Assessment
- host publication
- HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction
- series title
- HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction
- editor
- Osawa, Hirotaka ; Lindgren, Helena ; Steinfeld, Aaron ; Foster, Mary Ellen ; Okada, Shogo and Zhu, Haiyi
- pages
- 8 pages
- publisher
- Association for Computing Machinery (ACM)
- conference name
- 13th International Conference on Human-Agent Interaction, HAI 2025
- conference location
- Yokohama, Japan
- conference dates
- 2025-11-10 - 2025-11-13
- external identifiers
-
- scopus:105027383267
- ISBN
- 9798400721786
- DOI
- 10.1145/3765766.3765772
- language
- English
- LU publication?
- yes
- id
- 7adf9a22-7f3f-4fc0-b2ca-f20cf511c3be
- date added to LUP
- 2026-03-16 10:19:47
- date last changed
- 2026-03-16 10:19:47
@inproceedings{7adf9a22-7f3f-4fc0-b2ca-f20cf511c3be,
abstract = {{<p>The emergence of large language models (LLMs) has made it easier than ever to create chatbots capable of generating human-like responses to user inputs. Moreover, improvements in text-to-speech and speech-to-text make it possible to converse with these systems, not just in text but also through speech. These improvements have led to an increase in chatbot applications across various contexts, such as customer service and healthcare. This study examined the tendency to anthropomorphize chatbots in a mental health assessment context. Participants were randomized to interact with the chatbot via a text-based or voice-based interface. Neurotypical individuals (n = 62) and individuals with ADHD (n = 45) were recruited. The analysis revealed a significant Modality × Neurotype interaction, indicating that modality affected the groups differently. Follow-up simple-effects analyses suggested that ADHD participants tended to anthropomorphize less in the voice condition than the text condition, whereas neurotypical participants showed no reliable difference between modalities. Because response latency differed across conditions, causal attributions to modality alone cannot be made. We discuss response timing as a likely driver and implications for inclusive chatbot design.</p>}},
author = {{Holmberg, Linus and Sikström, Sverker and Riveiro, Maria}},
booktitle = {{HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction}},
editor = {{Osawa, Hirotaka and Lindgren, Helena and Steinfeld, Aaron and Foster, Mary Ellen and Okada, Shogo and Zhu, Haiyi}},
isbn = {{9798400721786}},
keywords = {{ADHD; Anthropomorphism; Chatbot; Human-Computer Interaction; Mental Health Assessment}},
language = {{eng}},
month = {{01}},
pages = {{50--57}},
publisher = {{Association for Computing Machinery (ACM)}},
series = {{HAI 2025 - Proceedings of the 13th International Conference on Human-Agent Interaction}},
title = {{Speaking or Writing : Do Response Times Influence Anthropomorphism Differently for ADHD and Neurotypical Users in a Mental Health Chatbot?}},
url = {{http://dx.doi.org/10.1145/3765766.3765772}},
doi = {{10.1145/3765766.3765772}},
year = {{2026}},
}