Nowadays, conversational agents are solutions that can provide a highly valuable addition to the existing healthcare services to assist the elderly in following their care plans and gradually changing adverse patterns of behaviour. Nevertheless, the development of a conversation agent in the healthcare domain presents several technical, design and linguistic challenges. In our paper, we describe a chatbot conversing with elderly persons, with age-related problems. Charlie, the name of our chatbot, has been designed to provide the elderly with companionship through innovative strategies based on gamification, active notifications, and promotion of self-compassion that can be explored for preventive mental healthcare. Moreover, Charlie can be used to monitor meaningful or anomalous situations that can affect aged people. To specify these situations in the paper we describe a web application that enables medical assistants and relatives to create rules that depend on data gathered by Charlie such as the number of required news, followed tips, completed games, but also biometrical data such as the number of steps made during the day, burned calories or the number of hours of sleep. To help caregivers in creating these rules, we are studying how to endow our web app with a recommendation service for predicting recurring anomalous situations and, accordingly, provide suggestions on which characteristics the elderly will have to change to improve their lifestyle.

Design of a Chatbot to Assist the Elderly / S. Valtolina, M. Marchionna (LECTURE NOTES IN COMPUTER SCIENCE). - In: End-User Development / [a cura di] D. Fogli, D. Tetteroo, B.R. Barricelli, S. Borsci, P. Markopoulos, G.A. Papadopoulos. - [s.l] : Springer International Publishing, 2021. - ISBN 9783030798406. - pp. 153-168 (( Intervento presentato al 8. convegno International Symposium, IS-EUD nel 2021 [10.1007/978-3-030-79840-6_10].

Design of a Chatbot to Assist the Elderly

S. Valtolina
;
2021

Abstract

Nowadays, conversational agents are solutions that can provide a highly valuable addition to the existing healthcare services to assist the elderly in following their care plans and gradually changing adverse patterns of behaviour. Nevertheless, the development of a conversation agent in the healthcare domain presents several technical, design and linguistic challenges. In our paper, we describe a chatbot conversing with elderly persons, with age-related problems. Charlie, the name of our chatbot, has been designed to provide the elderly with companionship through innovative strategies based on gamification, active notifications, and promotion of self-compassion that can be explored for preventive mental healthcare. Moreover, Charlie can be used to monitor meaningful or anomalous situations that can affect aged people. To specify these situations in the paper we describe a web application that enables medical assistants and relatives to create rules that depend on data gathered by Charlie such as the number of required news, followed tips, completed games, but also biometrical data such as the number of steps made during the day, burned calories or the number of hours of sleep. To help caregivers in creating these rules, we are studying how to endow our web app with a recommendation service for predicting recurring anomalous situations and, accordingly, provide suggestions on which characteristics the elderly will have to change to improve their lifestyle.
End-user development; Virtual assistants; CUI – conversational interface in healthcare; AI for HCI
Settore INF/01 - Informatica
2021
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
Valtolina-Marchionna2021_Chapter_DesignOfAChatbotToAssistTheEld.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 2.01 MB
Formato Adobe PDF
2.01 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/854798
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact