Thanks to psychosocial profiling and the identification of latent dimensions, this project aims to create messages consistent with the needs and psychological motivations of the recipients, and aimed at increasing behaviors that are useful for health, well-being and sustainability. The application of specific machine learning methods based on Deep Reinforcement Learning techniques also makes it possible to convert quantitative psycho-social models into adaptive digital interaction strategies based on personalized exchanges.
The project is funded by PwC and involves collaboration between engineers, psychologists, artificial intelligence and data science experts, and companies engaged in the insurance sector.
Applying psychology of persuasion to conversational agents through reinforcement learning: An exploratory study
Di Massimo, F., Carfora, V., Catellani, P., & Piastra, M. (2019). CEUR – Workshop Proceedings, 2481, 27.
Dialogue management in conversational agents through psychology of persuasion and machine learning
Carfora, V., Di Massimo, F., Rastelli, R., Catellani, P., & Piastra, M. (2020). Multimedia Tools and Applications, 39, 35949-35971.
Individual differences in regulatory focus predict health insurance purchasing intention.
Buscicchio, G., Bertolotti, M., & Catellani, P. (under review).