Exploring and comparing machine learning approaches for predicting mood over time

Ward van Breda, Johnno Pastor, Mark Hoogendoorn, Jeroen Ruwaard, Joost Asselbergs, Heleen Riper

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Mental health related problems are responsible for great sorrow for patients and social surrounding involved. The costs for society are estimated to be 2.5 trillion dollar worldwide. More detailed data about the mental states and behaviour is becoming available due to technological developments, e.g. using Ecological Momentary Assessments. Unfortunately this wealth of data is not utilized: data-driven predictive models for short-term developments could contribute to more personalized interventions, but are rarely seen. In this paper we study how modern machine learning techniques can contribute to better models for predicting shortterm mood in the context of depression. The models are based on data obtained from an experiment among 27 participants. During the study frequent mood assessments were performed and usage and sensor data of the mobile phone was recorded. Results show that much can be improved before fine-grained mood prediction is useful within E-health applications. Subsequently important next steps are identified.

Original languageEnglish
Title of host publicationInnovation in Medicine and Healthcare 2016
EditorsLakhmi C. Jain, Robert J. Howlett, Lakhmi C. Jain, Yen-Wei Chen, Satoshi Tanaka, Lakhmi C. Jain
PublisherSpringer Science and Business Media Deutschland GmbH
Pages37-47
Number of pages11
ISBN (Print)9783319396866
DOIs
Publication statusPublished - 1 Jan 2016
Event4th KES International Conference on Innovation in Medicine and Healthcare, InMed 2016 - Tenerife, Spain
Duration: 15 Jun 201617 Jun 2016

Publication series

NameSmart Innovation, Systems and Technologies
Volume60
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference4th KES International Conference on Innovation in Medicine and Healthcare, InMed 2016
CountrySpain
CityTenerife
Period15/06/201617/06/2016

Cite this

van Breda, W., Pastor, J., Hoogendoorn, M., Ruwaard, J., Asselbergs, J., & Riper, H. (2016). Exploring and comparing machine learning approaches for predicting mood over time. In L. C. Jain, R. J. Howlett, L. C. Jain, Y-W. Chen, S. Tanaka, & L. C. Jain (Eds.), Innovation in Medicine and Healthcare 2016 (pp. 37-47). (Smart Innovation, Systems and Technologies; Vol. 60). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-39687-3_4
van Breda, Ward ; Pastor, Johnno ; Hoogendoorn, Mark ; Ruwaard, Jeroen ; Asselbergs, Joost ; Riper, Heleen. / Exploring and comparing machine learning approaches for predicting mood over time. Innovation in Medicine and Healthcare 2016. editor / Lakhmi C. Jain ; Robert J. Howlett ; Lakhmi C. Jain ; Yen-Wei Chen ; Satoshi Tanaka ; Lakhmi C. Jain. Springer Science and Business Media Deutschland GmbH, 2016. pp. 37-47 (Smart Innovation, Systems and Technologies).
@inproceedings{5e36549c0a71437aa65830210cb216cf,
title = "Exploring and comparing machine learning approaches for predicting mood over time",
abstract = "Mental health related problems are responsible for great sorrow for patients and social surrounding involved. The costs for society are estimated to be 2.5 trillion dollar worldwide. More detailed data about the mental states and behaviour is becoming available due to technological developments, e.g. using Ecological Momentary Assessments. Unfortunately this wealth of data is not utilized: data-driven predictive models for short-term developments could contribute to more personalized interventions, but are rarely seen. In this paper we study how modern machine learning techniques can contribute to better models for predicting shortterm mood in the context of depression. The models are based on data obtained from an experiment among 27 participants. During the study frequent mood assessments were performed and usage and sensor data of the mobile phone was recorded. Results show that much can be improved before fine-grained mood prediction is useful within E-health applications. Subsequently important next steps are identified.",
author = "{van Breda}, Ward and Johnno Pastor and Mark Hoogendoorn and Jeroen Ruwaard and Joost Asselbergs and Heleen Riper",
year = "2016",
month = "1",
day = "1",
doi = "10.1007/978-3-319-39687-3_4",
language = "English",
isbn = "9783319396866",
series = "Smart Innovation, Systems and Technologies",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "37--47",
editor = "Jain, {Lakhmi C.} and Howlett, {Robert J.} and Jain, {Lakhmi C.} and Yen-Wei Chen and Satoshi Tanaka and Jain, {Lakhmi C.}",
booktitle = "Innovation in Medicine and Healthcare 2016",
address = "Germany",

}

van Breda, W, Pastor, J, Hoogendoorn, M, Ruwaard, J, Asselbergs, J & Riper, H 2016, Exploring and comparing machine learning approaches for predicting mood over time. in LC Jain, RJ Howlett, LC Jain, Y-W Chen, S Tanaka & LC Jain (eds), Innovation in Medicine and Healthcare 2016. Smart Innovation, Systems and Technologies, vol. 60, Springer Science and Business Media Deutschland GmbH, pp. 37-47, 4th KES International Conference on Innovation in Medicine and Healthcare, InMed 2016, Tenerife, Spain, 15/06/2016. https://doi.org/10.1007/978-3-319-39687-3_4

Exploring and comparing machine learning approaches for predicting mood over time. / van Breda, Ward; Pastor, Johnno; Hoogendoorn, Mark; Ruwaard, Jeroen; Asselbergs, Joost; Riper, Heleen.

Innovation in Medicine and Healthcare 2016. ed. / Lakhmi C. Jain; Robert J. Howlett; Lakhmi C. Jain; Yen-Wei Chen; Satoshi Tanaka; Lakhmi C. Jain. Springer Science and Business Media Deutschland GmbH, 2016. p. 37-47 (Smart Innovation, Systems and Technologies; Vol. 60).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Exploring and comparing machine learning approaches for predicting mood over time

AU - van Breda, Ward

AU - Pastor, Johnno

AU - Hoogendoorn, Mark

AU - Ruwaard, Jeroen

AU - Asselbergs, Joost

AU - Riper, Heleen

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Mental health related problems are responsible for great sorrow for patients and social surrounding involved. The costs for society are estimated to be 2.5 trillion dollar worldwide. More detailed data about the mental states and behaviour is becoming available due to technological developments, e.g. using Ecological Momentary Assessments. Unfortunately this wealth of data is not utilized: data-driven predictive models for short-term developments could contribute to more personalized interventions, but are rarely seen. In this paper we study how modern machine learning techniques can contribute to better models for predicting shortterm mood in the context of depression. The models are based on data obtained from an experiment among 27 participants. During the study frequent mood assessments were performed and usage and sensor data of the mobile phone was recorded. Results show that much can be improved before fine-grained mood prediction is useful within E-health applications. Subsequently important next steps are identified.

AB - Mental health related problems are responsible for great sorrow for patients and social surrounding involved. The costs for society are estimated to be 2.5 trillion dollar worldwide. More detailed data about the mental states and behaviour is becoming available due to technological developments, e.g. using Ecological Momentary Assessments. Unfortunately this wealth of data is not utilized: data-driven predictive models for short-term developments could contribute to more personalized interventions, but are rarely seen. In this paper we study how modern machine learning techniques can contribute to better models for predicting shortterm mood in the context of depression. The models are based on data obtained from an experiment among 27 participants. During the study frequent mood assessments were performed and usage and sensor data of the mobile phone was recorded. Results show that much can be improved before fine-grained mood prediction is useful within E-health applications. Subsequently important next steps are identified.

UR - http://www.scopus.com/inward/record.url?scp=84979034767&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-39687-3_4

DO - 10.1007/978-3-319-39687-3_4

M3 - Conference contribution

SN - 9783319396866

T3 - Smart Innovation, Systems and Technologies

SP - 37

EP - 47

BT - Innovation in Medicine and Healthcare 2016

A2 - Jain, Lakhmi C.

A2 - Howlett, Robert J.

A2 - Jain, Lakhmi C.

A2 - Chen, Yen-Wei

A2 - Tanaka, Satoshi

A2 - Jain, Lakhmi C.

PB - Springer Science and Business Media Deutschland GmbH

ER -

van Breda W, Pastor J, Hoogendoorn M, Ruwaard J, Asselbergs J, Riper H. Exploring and comparing machine learning approaches for predicting mood over time. In Jain LC, Howlett RJ, Jain LC, Chen Y-W, Tanaka S, Jain LC, editors, Innovation in Medicine and Healthcare 2016. Springer Science and Business Media Deutschland GmbH. 2016. p. 37-47. (Smart Innovation, Systems and Technologies). https://doi.org/10.1007/978-3-319-39687-3_4