Towards the personalisation of the chatbot-patient relationship
Conversational agents (CAs) for chronic disease management are receiving increasing attention in academia and industry. However, long-term adherence to CAs is still a challenge and to be explored. Personalisation of CAs has the potential to improve long-term adherence and, with it, user satisfaction, task efficiency, perceived benefits, and intended behaviour change. Research on personalised CAs has already addressed different aspects, such as personalised recommendations or anthropomorphic cues. However, detailed information on interaction styles between patients and CAs in the role of a medical healthcare professional is scant. Such interaction styles play an essential role for patient satisfaction, treatment adherence and outcome, as has been shown for physician-patient interactions. Currently, it is not clear (i) whether chronically ill patients prefer a CA with either a paternalistic, informative, interpretive, or deliberative interaction style, and (ii) which factors influence these preferences.
The objective of the paper titled “Personalization of Conversational Agent-Patient Interaction Styles for Chronic Disease Management: Results from two studies with COPD patients“, comprising of two consecutive studies, is to investigate preferences for CA-delivered interaction styles by chronically ill patients. The first study was conducted paper-based and explored preferences of COPD-patients for paternalistic, informative, interpretive, and deliberative CA-delivered interaction styles. Based on these results, a second study assessed the effect of the paternalistic and deliberative interaction style on the relationship quality between the CA and patients via hierarchical multiple linear regression analyses in an online experiment with COPD patients. Patients’ socio-demographic and disease-specific characteristics served as moderator variables.
The obtained results indicate that age and a patient’s personal disease experience inform which interaction style the patient should be paired with to achieve increased interaction related outcomes with the CA. These results allow to design personalised healthcare CAs with the goal to increase long-term adherence to health-promoting behaviour.
Gross, C., Schachner, T., Hasl, A., Kohlbrenner, D., Clarenbach, C.F., Kowatsch, T., von Wangenheim, F., Personalization of Conversational Agent-Patient Interaction Styles for Chronic Disease Management: Results from two studies with COPD patients, JMIR Preprints. 19/12/2020:26643 10.2196/preprints.26643. [PDF]
Schachner, T., Gross, C., Hasl, A., von Wangenheim, F., Kowatsch, T., Deliberative and Paternalistic Interaction Styles for Conversational Agents in Digital Health: Procedure and Validation Through a Web-Based Experiment, Journal of Medical Internet Research (JMIR), 23(1):e22919, 10.2196/22919. [PDF]
Kowatsch, T., Schachner, T., Harperink, S., Barata, F., Dittler, U., Xiao, G., Stanger, C., Oswald, H., Fleisch, E., von Wangenheim, F., Möller, A., Conversational Agents as Mediating Social Actors in Chronic Disease Management Involving Healthcare Professionals, Patients, and Family Members: Intervention Design and Results from a Multi-site, Single-arm Feasibility Study, Journal of Medical Internet Research (accepted Jan 23, 2021) Link to the Preprint: 10.2196/preprints.25060 (forthcoming). [PDF]
Schachner, T., Keller, R., von Wangenheim, F., Artificial Intelligence-Based Conversational Agents for Chronic Conditions: Systematic Literature Review, Journal of Medical Internet Research;22(9):e20701, doi.org/10.2196/20701. [PDF]
Stieger, M., Flückiger, C., Rüegger, D., Kowatsch, T., Roberts, B.W., Allemand, M., Changing Personality Traits with the Help of a Digital Personality Change Intervention, Proceedings of the National Academy of Sciences of the United States of America (PNAS) 118(8):e2017548118 10.1073/pnas.2017548118 (Preprint: 10.31234/osf.io/sur2j.