EEMCS

Home > Publications
Home University of Twente
Education
Research
Prospective Students
Jobs
Publications
Intranet (internal)
 
 Nederlands
 Contact
 Search
 Organisation

EEMCS EPrints Service


25956 Tailored motivational message generation: A model and practical framework for real-time physical activity coaching
Home Policy Brochure Browse Search User Area Contact Help

op den Akker, H. and Cabrita, M. and op den Akker, H.J.A. and Jones, V.M. and Hermens, H.J. (2015) Tailored motivational message generation: A model and practical framework for real-time physical activity coaching. Journal of Biomedical Informatics, 55. pp. 104-115. ISSN 1532-0464 *** ISI Impact 2,447 ***

Full text available as:

PDF

1421 Kb
Open Access



Official URL: http://dx.doi.org/10.1016/j.jbi.2015.03.005

Exported to Metis

Abstract

This paper presents a comprehensive and practical framework for automatic generation of real-time tailored messages in behavior change applications. Basic aspects of motivational messages are time, intention, content and presentation. Tailoring of messages to the individual user may involve all aspects of communication. A linear modular system is presented for generating such messages. It is explained how properties of user and context are taken into account in each of the modules of the system and how they affect the linguistic presentation of the generated messages. The model of motivational messages presented is based on an analysis of existing literature as well as the analysis of a corpus of motivational messages used in previous studies. The model extends existing ‘ontology-based’ approaches to message generation for real-time coaching systems found in the literature. Practical examples are given on how simple tailoring rules can be implemented throughout the various stages of the framework. Such examples can guide further research by clarifying what it means to use e.g. user targeting to tailor a message. As primary example we look at the issue of promoting daily physical activity. Future work is pointed out in applying the present model and framework, defining efficient ways of evaluating individual tailoring components, and improving effectiveness through the creation of accurate and complete user- and context models.

Item Type:Article
Research Group:EWI-BSS: Biomedical Signals and Systems, EWI-HMI: Human Media Interaction
Research Program:CTIT-General
Uncontrolled Keywords:Motivational messages, Physical activity, Persuasive systems, EHealth, Telemedicine
ID Code:25956
Status:Published
Deposited On:01 May 2015
Refereed:Yes
International:Yes
ISI Impact Factor:2,447
More Information:statisticsmetis

Export this item as:

To correct this item please ask your editor

Repository Staff Only: edit this item