How to predict mood? Delving into features of smartphone-based data

Dennis Becker, Burkhardt Funk, Heleen Riper, Vincent Bremer, Joost Asselbergs, Jeroen Ruwaard

Research output: Contribution to conferencePaperAcademic

Abstract

Smartphones are increasingly utilized in society and enable scientists to record a wide range of behavioral and environmental information. These information, referred to as Unobtrusive Ecological Momentary Assessment Data, might support prediction procedures regarding the mood level of users and simultaneously contribute to an enhancement of therapy strategies. In this paper, we analyze how the mood level of healthy clients is affected by unobtrusive measures and how this kind of data contributes to the prediction performance of various statistical models (Bayesian methods, Lasso procedures, etc.). We conduct analyses on a non-user and a user level. We then compare the models by utilizing introduced performance measures. Our findings indicate that the prediction performance increases when considering individual users. However, the implemented models only perform slightly better than the introduced mean model. Indicated by feature selection methods, we assume that more meaningful variables regarding the outcome can potentially increase prediction performance.

Original languageEnglish
Publication statusPublished - 1 Jan 2016
Event22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016 - San Diego, United States
Duration: 11 Aug 201614 Aug 2016

Conference

Conference22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016
CountryUnited States
CitySan Diego
Period11/08/201614/08/2016

Cite this

Becker, D., Funk, B., Riper, H., Bremer, V., Asselbergs, J., & Ruwaard, J. (2016). How to predict mood? Delving into features of smartphone-based data. Paper presented at 22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016, San Diego, United States.
Becker, Dennis ; Funk, Burkhardt ; Riper, Heleen ; Bremer, Vincent ; Asselbergs, Joost ; Ruwaard, Jeroen. / How to predict mood? Delving into features of smartphone-based data. Paper presented at 22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016, San Diego, United States.
@conference{a5c92c7379da4dcfae3470b7b739f121,
title = "How to predict mood? Delving into features of smartphone-based data",
abstract = "Smartphones are increasingly utilized in society and enable scientists to record a wide range of behavioral and environmental information. These information, referred to as Unobtrusive Ecological Momentary Assessment Data, might support prediction procedures regarding the mood level of users and simultaneously contribute to an enhancement of therapy strategies. In this paper, we analyze how the mood level of healthy clients is affected by unobtrusive measures and how this kind of data contributes to the prediction performance of various statistical models (Bayesian methods, Lasso procedures, etc.). We conduct analyses on a non-user and a user level. We then compare the models by utilizing introduced performance measures. Our findings indicate that the prediction performance increases when considering individual users. However, the implemented models only perform slightly better than the introduced mean model. Indicated by feature selection methods, we assume that more meaningful variables regarding the outcome can potentially increase prediction performance.",
keywords = "Bayesian modeling, E-mental-health, Mood prediction, Smartphone-based data, Unobtrusive ema",
author = "Dennis Becker and Burkhardt Funk and Heleen Riper and Vincent Bremer and Joost Asselbergs and Jeroen Ruwaard",
year = "2016",
month = "1",
day = "1",
language = "English",
note = "22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016 ; Conference date: 11-08-2016 Through 14-08-2016",

}

Becker, D, Funk, B, Riper, H, Bremer, V, Asselbergs, J & Ruwaard, J 2016, 'How to predict mood? Delving into features of smartphone-based data' Paper presented at 22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016, San Diego, United States, 11/08/2016 - 14/08/2016, .

How to predict mood? Delving into features of smartphone-based data. / Becker, Dennis; Funk, Burkhardt; Riper, Heleen; Bremer, Vincent; Asselbergs, Joost; Ruwaard, Jeroen.

2016. Paper presented at 22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016, San Diego, United States.

Research output: Contribution to conferencePaperAcademic

TY - CONF

T1 - How to predict mood? Delving into features of smartphone-based data

AU - Becker, Dennis

AU - Funk, Burkhardt

AU - Riper, Heleen

AU - Bremer, Vincent

AU - Asselbergs, Joost

AU - Ruwaard, Jeroen

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Smartphones are increasingly utilized in society and enable scientists to record a wide range of behavioral and environmental information. These information, referred to as Unobtrusive Ecological Momentary Assessment Data, might support prediction procedures regarding the mood level of users and simultaneously contribute to an enhancement of therapy strategies. In this paper, we analyze how the mood level of healthy clients is affected by unobtrusive measures and how this kind of data contributes to the prediction performance of various statistical models (Bayesian methods, Lasso procedures, etc.). We conduct analyses on a non-user and a user level. We then compare the models by utilizing introduced performance measures. Our findings indicate that the prediction performance increases when considering individual users. However, the implemented models only perform slightly better than the introduced mean model. Indicated by feature selection methods, we assume that more meaningful variables regarding the outcome can potentially increase prediction performance.

AB - Smartphones are increasingly utilized in society and enable scientists to record a wide range of behavioral and environmental information. These information, referred to as Unobtrusive Ecological Momentary Assessment Data, might support prediction procedures regarding the mood level of users and simultaneously contribute to an enhancement of therapy strategies. In this paper, we analyze how the mood level of healthy clients is affected by unobtrusive measures and how this kind of data contributes to the prediction performance of various statistical models (Bayesian methods, Lasso procedures, etc.). We conduct analyses on a non-user and a user level. We then compare the models by utilizing introduced performance measures. Our findings indicate that the prediction performance increases when considering individual users. However, the implemented models only perform slightly better than the introduced mean model. Indicated by feature selection methods, we assume that more meaningful variables regarding the outcome can potentially increase prediction performance.

KW - Bayesian modeling

KW - E-mental-health

KW - Mood prediction

KW - Smartphone-based data

KW - Unobtrusive ema

UR - http://www.scopus.com/inward/record.url?scp=84987678538&partnerID=8YFLogxK

M3 - Paper

ER -

Becker D, Funk B, Riper H, Bremer V, Asselbergs J, Ruwaard J. How to predict mood? Delving into features of smartphone-based data. 2016. Paper presented at 22nd Americas Conference on Information Systems: Surfing the IT Innovation Wave, AMCIS 2016, San Diego, United States.