Abstract
Much of the research in the field of virtual coaching agents focuses on interactions between a single agent and the user of the application. Another approach could be to give each user a personal virtual coaching team. This makes it possible to present multiple perspectives, and to have coaches with different expertise debate with each other. This could make the content presented more engaging and the system more persuasive. However, currently guidelines and theory to base designs for content for virtual coaching teams on is scarce. In this paper we present a study in which we set out to design content for a virtual coaching team to talk about general health topics with older adults. We based the content for our study on our implementation of two different models from social psychology used to classify interactive behaviour: the Interaction Process Analysis (IPA) and Interpersonal Circumplex (IPC) models. After testing our implementation of the models with a pilot test, we conducted an online study with 242 older adult participants. We compared the content modelled using the IPA model to the content modelled using the IPC model. For the IPA modelled content compared to the IPC modelled content the virtual coaching team came across more positively, the quality of their coaching was perceived to be better, the interaction experience was rated as better, their ability to persuade was better, and their group cohesion (task and social cohesion) was perceived to be better. We conclude that the IPA model is preferred over the IPC model when designing health coaching content for virtual coaching teams, and discuss possible reasons why. Furthermore, we recommend designers of health coaching content to test other models to base content designs on, and to measure the impact of differently modelled content in both more and less sophisticated coaching systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bickmore, T., Gruber, A., Picard, R.: Establishing the computer-patient working alliance in automated health behavior change interventions. Patient Educ. Couns. 59(1), 21–30 (2005)
Bickmore, T., Schulman, D., Yin, L.: Maintaining engagement in long-term interventions with relational agents. Appl. Artif. Intell. 24(6), 648–666 (2010)
Gardiner, P.M., et al.: Engaging women with an embodied conversational agent to deliver mindfulness and lifestyle recommendations: a feasibility randomized control trial. Patient Educ. Couns. 100(9), 1720–1729 (2017)
Huizing, G., Klaassen, R., Heylen, D.: Multi-perspective persuasion by a council of virtual coaches. In: Proceedings of the Eighth International Workshop on Behavior Change Support Systems, Aalborg, Denmark, 21 April. CEUR-WS.org (2020). http://CEUR-WS.org/Vol-2662/BCSS2020_paper2.pdf
André, E., Rist, T., van Mulken, S., Klesen, M., Baldes, S.: The Automated Design of Believable Dialogues for Animated Presentation Teams. Embodied Conversational Agents, Cambridge, MA, USA, pp. 220–255 (2001)
Kantharaju, R., Pease, D., De Franco, D., Pelachaud, C.: Is two better than one? Effects of multiple agents on user persuasion. In: Proceedings of the 18th International Conference on Intelligent Virtual Agents, CoRR abs/1904.05248 (2018)
Losch, S., Traut-Mattausch, E., Mühlberger, M.D., Jonas, E.: Comparing the effectiveness of individual coaching, self-coaching, and group training: How leadership makes the difference. Front. Psychol. 7, 629 (2016). https://doi.org/10.3389/fpsyg.2016.00629
Bales, R.F.: Interaction Process Analysis: A Method for the Study of Small Groups, 1st edn. Addison-Wesley Press, Inc., Cambridge (1951)
Leary, T.: Interpersonal Diagnosis of Personality: A Functional Theory and Methodology for Personality Evaluation, 1st edn. Wipf and Stock Publishers, Eugene (2004)
Hung, H., Gatica-Perez, D.: Estimating cohesion in small groups using audio-visual nonverbal behavior. IEEE Trans. Multimed. 12(6), 563–575 (2010)
Official Godspeed Questionnaire Series. http://www.bartneck.de/2008/03/11/the-godspeed-questionnaire-series/. Accessed 15 Feb 2021
Aneja, D., McDuff, D., Czerwinski, M.: Conversational error analysis in human-agent interaction. In: Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents (IVA 2020), Article 3, pp. 1–8. Association for Computing Machinery, New York (2020). https://doi.org/10.1145/3383652.3423901
Côte, J., Yardley, J., Hay, J., Sedgwick, W., Baker, J.: An exploratory examination of the coaching behaviour scale for sport. Avante Res. Note 5(2), 82–92 (1999)
Faul, F., Erdfelder, E., Lang, A.G., Buchner, A.: G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behav. Res. Methods 39, 175–191 (2007)
Benjamini, Y., Hochberg, Y.: Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. Roy. Stat. Soc.: Ser. B (Methodol.) 57(1), 289–300 (1995)
Smith, C.L.: How coaching helps leadership resilience: the leadership perspective. Int. Coach. Psychol. Rev. 10(1), 6–19 (2015)
Parekh, N., Gahagan, B., Ward, L., Ali, K.: ‘They must help if the doctor gives them to you’: a qualitative study of the older person’s lived experience of medication-related problems. Age Ageing 48(1), 147–151 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Huizing, G., Klaassen, R., Heylen, D. (2021). Designing Effective Dialogue Content for a Virtual Coaching Team Using the Interaction Process Analysis and Interpersonal Circumplex Models. In: Ali, R., Lugrin, B., Charles, F. (eds) Persuasive Technology. PERSUASIVE 2021. Lecture Notes in Computer Science(), vol 12684. Springer, Cham. https://doi.org/10.1007/978-3-030-79460-6_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-79460-6_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-79459-0
Online ISBN: 978-3-030-79460-6
eBook Packages: Computer ScienceComputer Science (R0)