In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study

BackgroundEmotions and mood are important for overall well-being. Therefore, the search for continuous, effortless emotion prediction methods is an important field of study. Mobile sensing provides a promising tool and can capture one of the most telling signs of emotion: lan...

Full description

Bibliographic Details
Main Authors: Chiara Carlier, Koen Niemeijer, Merijn Mestdagh, Michael Bauwens, Peter Vanbrabant, Luc Geurts, Toon van Waterschoot, Peter Kuppens
Format: Article
Language:English
Published: JMIR Publications 2022-02-01
Series:JMIR Mental Health
Online Access:https://mental.jmir.org/2022/2/e31724
_version_ 1827858607001042944
author Chiara Carlier
Koen Niemeijer
Merijn Mestdagh
Michael Bauwens
Peter Vanbrabant
Luc Geurts
Toon van Waterschoot
Peter Kuppens
author_facet Chiara Carlier
Koen Niemeijer
Merijn Mestdagh
Michael Bauwens
Peter Vanbrabant
Luc Geurts
Toon van Waterschoot
Peter Kuppens
author_sort Chiara Carlier
collection DOAJ
description BackgroundEmotions and mood are important for overall well-being. Therefore, the search for continuous, effortless emotion prediction methods is an important field of study. Mobile sensing provides a promising tool and can capture one of the most telling signs of emotion: language. ObjectiveThe aim of this study is to examine the separate and combined predictive value of mobile-sensed language data sources for detecting both momentary emotional experience as well as global individual differences in emotional traits and depression. MethodsIn a 2-week experience sampling method study, we collected self-reported emotion ratings and voice recordings 10 times a day, continuous keyboard activity, and trait depression severity. We correlated state and trait emotions and depression and language, distinguishing between speech content (spoken words), speech form (voice acoustics), writing content (written words), and writing form (typing dynamics). We also investigated how well these features predicted state and trait emotions using cross-validation to select features and a hold-out set for validation. ResultsOverall, the reported emotions and mobile-sensed language demonstrated weak correlations. The most significant correlations were found between speech content and state emotions and between speech form and state emotions, ranging up to 0.25. Speech content provided the best predictions for state emotions. None of the trait emotion–language correlations remained significant after correction. Among the emotions studied, valence and happiness displayed the most significant correlations and the highest predictive performance. ConclusionsAlthough using mobile-sensed language as an emotion marker shows some promise, correlations and predictive R2 values are low.
first_indexed 2024-03-12T12:57:36Z
format Article
id doaj.art-7bdff9b7a427489fb3b857d7470c40e3
institution Directory Open Access Journal
issn 2368-7959
language English
last_indexed 2024-03-12T12:57:36Z
publishDate 2022-02-01
publisher JMIR Publications
record_format Article
series JMIR Mental Health
spelling doaj.art-7bdff9b7a427489fb3b857d7470c40e32023-08-28T20:47:06ZengJMIR PublicationsJMIR Mental Health2368-79592022-02-0192e3172410.2196/31724In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field StudyChiara Carlierhttps://orcid.org/0000-0003-4985-6240Koen Niemeijerhttps://orcid.org/0000-0002-0816-534XMerijn Mestdaghhttps://orcid.org/0000-0001-5077-861XMichael Bauwenshttps://orcid.org/0000-0002-6340-7516Peter Vanbrabanthttps://orcid.org/0000-0003-0217-3303Luc Geurtshttps://orcid.org/0000-0002-9608-9147Toon van Waterschoothttps://orcid.org/0000-0002-6323-7350Peter Kuppenshttps://orcid.org/0000-0002-2363-2356 BackgroundEmotions and mood are important for overall well-being. Therefore, the search for continuous, effortless emotion prediction methods is an important field of study. Mobile sensing provides a promising tool and can capture one of the most telling signs of emotion: language. ObjectiveThe aim of this study is to examine the separate and combined predictive value of mobile-sensed language data sources for detecting both momentary emotional experience as well as global individual differences in emotional traits and depression. MethodsIn a 2-week experience sampling method study, we collected self-reported emotion ratings and voice recordings 10 times a day, continuous keyboard activity, and trait depression severity. We correlated state and trait emotions and depression and language, distinguishing between speech content (spoken words), speech form (voice acoustics), writing content (written words), and writing form (typing dynamics). We also investigated how well these features predicted state and trait emotions using cross-validation to select features and a hold-out set for validation. ResultsOverall, the reported emotions and mobile-sensed language demonstrated weak correlations. The most significant correlations were found between speech content and state emotions and between speech form and state emotions, ranging up to 0.25. Speech content provided the best predictions for state emotions. None of the trait emotion–language correlations remained significant after correction. Among the emotions studied, valence and happiness displayed the most significant correlations and the highest predictive performance. ConclusionsAlthough using mobile-sensed language as an emotion marker shows some promise, correlations and predictive R2 values are low.https://mental.jmir.org/2022/2/e31724
spellingShingle Chiara Carlier
Koen Niemeijer
Merijn Mestdagh
Michael Bauwens
Peter Vanbrabant
Luc Geurts
Toon van Waterschoot
Peter Kuppens
In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
JMIR Mental Health
title In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
title_full In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
title_fullStr In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
title_full_unstemmed In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
title_short In Search of State and Trait Emotion Markers in Mobile-Sensed Language: Field Study
title_sort in search of state and trait emotion markers in mobile sensed language field study
url https://mental.jmir.org/2022/2/e31724
work_keys_str_mv AT chiaracarlier insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT koenniemeijer insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT merijnmestdagh insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT michaelbauwens insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT petervanbrabant insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT lucgeurts insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT toonvanwaterschoot insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy
AT peterkuppens insearchofstateandtraitemotionmarkersinmobilesensedlanguagefieldstudy