The healthcare sector is increasingly utilizing bots for patient management, chronic disease management, and health advice, providing 24/7 support and immediate medical responses. The language of these bots is crucial, impacting patient comfort, understanding, and trust. This paper examines the optimal communication style for medical chatbots and addresses four research questions: the influence of personal traits and disease types on healthcare communication perception, their combined effect, and the role of AI in improving communications. A Likert-scale questionnaire assessed user personality and perception across 15 scenarios. Results from 49 participants indicate that effective personalization requires considering both personality and disease type. AI-based clustering further refines personalization, revealing distinct preferences, such as females preferring empathetic communication and males preferring factual communication. This study highlights the necessity of integrating personality traits and medical conditions in chatbot communication to enhance patient engagement and healthcare outcomes.
Conversational Skills of LLM-based Healthcare Chatbot for Personalized Communications / Furini, Marco; Mariani, Michele; Montagna, Sara; Ferretti, Stefano. - (2024), pp. 429-432. (Intervento presentato al convegno International Conference on Information Technology for Social Good tenutosi a Brema nel 04/09/2024) [10.1145/3677525.3678693].
Conversational Skills of LLM-based Healthcare Chatbot for Personalized Communications
Furini, Marco
;Mariani, Michele;
2024
Abstract
The healthcare sector is increasingly utilizing bots for patient management, chronic disease management, and health advice, providing 24/7 support and immediate medical responses. The language of these bots is crucial, impacting patient comfort, understanding, and trust. This paper examines the optimal communication style for medical chatbots and addresses four research questions: the influence of personal traits and disease types on healthcare communication perception, their combined effect, and the role of AI in improving communications. A Likert-scale questionnaire assessed user personality and perception across 15 scenarios. Results from 49 participants indicate that effective personalization requires considering both personality and disease type. AI-based clustering further refines personalization, revealing distinct preferences, such as females preferring empathetic communication and males preferring factual communication. This study highlights the necessity of integrating personality traits and medical conditions in chatbot communication to enhance patient engagement and healthcare outcomes.Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris