MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health

Darius Adam Rohani; Andrea Quemada Lopategui; Nanna Tuxen; Maria Faurholt-Jepsen; Lars V. Kessing; Jakob Eyvind Bardram

doi:10.1145/3313831.3376879

MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health

Darius Adam Rohani, Andrea Quemada Lopategui, Nanna Tuxen, Maria Faurholt-Jepsen, Lars V. Kessing, Jakob Eyvind Bardram

Psychiatric Centre Copenhagen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Depression is a leading cause of disability worldwide, which has inspired the design of mobile health (mHealth) applications for disease monitoring, prediction, and diagnosis. Less mHealth research has, however, focused on the treatment of depressive disorders. Clinical evidence shows that depressive symptoms can be reduced through a behavior change method known as Behavioral Activation (BA). This paper presents MUBS; a smartphone-based system for BA, which specifically contributes a personalized content-based activity recommendation model using a unique list of validated activities. An 8-week feasibility study with 17 depressive patients provided detailed insight into how MUBS provided inspiration and motivation for planning and engaging in more pleasant activities, thereby facilitating the core components of BA. Based on this study, the paper discusses how recommender technology can be used in the design of mHealth technology for BA.

Original language	English
Title of host publication	CHI '20 : Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
Number of pages	13
Publisher	Association for Computing Machinery
Publication date	2020
Article number	750
ISBN (Electronic)	978-1-4503-6708-0
DOIs	https://doi.org/10.1145/3313831.3376879
Publication status	Published - 2020
Event	CHI '20: CHI Conference on Human Factors in Computing Systems - Honolulu, United States Duration: 25 Apr 2020 → 30 Apr 2020

Conference

Conference	CHI '20: CHI Conference on Human Factors in Computing Systems
Country/Territory	United States
City	Honolulu
Period	25/04/2020 → 30/04/2020

Keywords

Depression
Recommendation
Behavioral Activation
Planning
Activities
Well-being
Smartphone
Mental health

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3313831.3376879

OpenUrl availability

Full text

Cite this

Rohani, D. A., Quemada Lopategui, A., Tuxen, N., Faurholt-Jepsen, M., Kessing, L. V., & Bardram, J. E. (2020). MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health. In CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems Article 750 Association for Computing Machinery. https://doi.org/10.1145/3313831.3376879

@inproceedings{4cbe0338aa3e4e9e9bd5dea706956365,

title = "MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health",

abstract = "Depression is a leading cause of disability worldwide, which has inspired the design of mobile health (mHealth) applications for disease monitoring, prediction, and diagnosis. Less mHealth research has, however, focused on the treatment of depressive disorders. Clinical evidence shows that depressive symptoms can be reduced through a behavior change method known as Behavioral Activation (BA). This paper presents MUBS; a smartphone-based system for BA, which specifically contributes a personalized content-based activity recommendation model using a unique list of validated activities. An 8-week feasibility study with 17 depressive patients provided detailed insight into how MUBS provided inspiration and motivation for planning and engaging in more pleasant activities, thereby facilitating the core components of BA. Based on this study, the paper discusses how recommender technology can be used in the design of mHealth technology for BA.",

keywords = "Depression, Recommendation, Behavioral Activation, Planning, Activities, Well-being, Smartphone, Mental health",

author = "Rohani, {Darius Adam} and {Quemada Lopategui}, Andrea and Nanna Tuxen and Maria Faurholt-Jepsen and Kessing, {Lars V.} and Bardram, {Jakob Eyvind}",

year = "2020",

doi = "10.1145/3313831.3376879",

language = "English",

booktitle = "CHI '20",

publisher = "Association for Computing Machinery",

address = "United States",

note = "CHI '20: CHI Conference on Human Factors in Computing Systems ; Conference date: 25-04-2020 Through 30-04-2020",

}

Rohani, DA, Quemada Lopategui, A, Tuxen, N, Faurholt-Jepsen, M, Kessing, LV & Bardram, JE 2020, MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health. in CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems., 750, Association for Computing Machinery, CHI '20: CHI Conference on Human Factors in Computing Systems, Honolulu, Hawaii, United States, 25/04/2020. https://doi.org/10.1145/3313831.3376879

MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health. / Rohani, Darius Adam; Quemada Lopategui, Andrea; Tuxen, Nanna et al.
CHI '20: Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2020. 750.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health

AU - Rohani, Darius Adam

AU - Quemada Lopategui, Andrea

AU - Tuxen, Nanna

AU - Faurholt-Jepsen, Maria

AU - Kessing, Lars V.

AU - Bardram, Jakob Eyvind

PY - 2020

Y1 - 2020

N2 - Depression is a leading cause of disability worldwide, which has inspired the design of mobile health (mHealth) applications for disease monitoring, prediction, and diagnosis. Less mHealth research has, however, focused on the treatment of depressive disorders. Clinical evidence shows that depressive symptoms can be reduced through a behavior change method known as Behavioral Activation (BA). This paper presents MUBS; a smartphone-based system for BA, which specifically contributes a personalized content-based activity recommendation model using a unique list of validated activities. An 8-week feasibility study with 17 depressive patients provided detailed insight into how MUBS provided inspiration and motivation for planning and engaging in more pleasant activities, thereby facilitating the core components of BA. Based on this study, the paper discusses how recommender technology can be used in the design of mHealth technology for BA.

AB - Depression is a leading cause of disability worldwide, which has inspired the design of mobile health (mHealth) applications for disease monitoring, prediction, and diagnosis. Less mHealth research has, however, focused on the treatment of depressive disorders. Clinical evidence shows that depressive symptoms can be reduced through a behavior change method known as Behavioral Activation (BA). This paper presents MUBS; a smartphone-based system for BA, which specifically contributes a personalized content-based activity recommendation model using a unique list of validated activities. An 8-week feasibility study with 17 depressive patients provided detailed insight into how MUBS provided inspiration and motivation for planning and engaging in more pleasant activities, thereby facilitating the core components of BA. Based on this study, the paper discusses how recommender technology can be used in the design of mHealth technology for BA.

KW - Depression

KW - Recommendation

KW - Behavioral Activation

KW - Planning

KW - Activities

KW - Well-being

KW - Smartphone

KW - Mental health

U2 - 10.1145/3313831.3376879

DO - 10.1145/3313831.3376879

M3 - Article in proceedings

BT - CHI '20

PB - Association for Computing Machinery

T2 - CHI '20: CHI Conference on Human Factors in Computing Systems

Y2 - 25 April 2020 through 30 April 2020

ER -

MUBS: A Personalized Recommender System for Behavioral Activation in Mental Health

Abstract

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Fingerprint

Cite this