Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing

Introduction: Social isolation and loneliness (SI/L) are growing problems with serious health implications for older adults, especially in light of the COVID-19 pandemic. We examined transcripts from semi-structured interviews with 97 older adults (mean age 83 years) to identify linguistic features...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Varsha D. Badal, Camille Nebeker, Kaoru Shinkawa, Yasunori Yamada, Kelly E. Rentscher, Ho-Cheol Kim, Ellen E. Lee
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	artificial intelligence social connectedness gender loneliness NLP Social support Psychiatry RC435-571
Acceso en línea:	https://doaj.org/article/0da859c5faa443f9994bd6f6ffaa0946
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0da859c5faa443f9994bd6f6ffaa0946
record_format	dspace
spelling	oai:doaj.org-article:0da859c5faa443f9994bd6f6ffaa09462021-11-16T05:43:32ZDo Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing1664-064010.3389/fpsyt.2021.728732https://doaj.org/article/0da859c5faa443f9994bd6f6ffaa09462021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fpsyt.2021.728732/fullhttps://doaj.org/toc/1664-0640Introduction: Social isolation and loneliness (SI/L) are growing problems with serious health implications for older adults, especially in light of the COVID-19 pandemic. We examined transcripts from semi-structured interviews with 97 older adults (mean age 83 years) to identify linguistic features of SI/L.Methods: Natural Language Processing (NLP) methods were used to identify relevant interview segments (responses to specific questions), extract the type and number of social contacts and linguistic features such as sentiment, parts-of-speech, and syntactic complexity. We examined: (1) associations of NLP-derived assessments of social relationships and linguistic features with validated self-report assessments of social support and loneliness; and (2) important linguistic features for detecting individuals with higher level of SI/L by using machine learning (ML) models.Results: NLP-derived assessments of social relationships were associated with self-reported assessments of social support and loneliness, though these associations were stronger in women than in men. Usage of first-person plural pronouns was negatively associated with loneliness in women and positively associated with emotional support in men. ML analysis using leave-one-out methodology showed good performance (F1 = 0.73, AUC = 0.75, specificity = 0.76, and sensitivity = 0.69) of the binary classification models in detecting individuals with higher level of SI/L. Comparable performance were also observed when classifying social and emotional support measures. Using ML models, we identified several linguistic features (including use of first-person plural pronouns, sentiment, sentence complexity, and sentence similarity) that most strongly predicted scores on scales for loneliness and social support.Discussion: Linguistic data can provide unique insights into SI/L among older adults beyond scale-based assessments, though there are consistent gender differences. Future research studies that incorporate diverse linguistic features as well as other behavioral data-streams may be better able to capture the complexity of social functioning in older adults and identification of target subpopulations for future interventions. Given the novelty, use of NLP should include prospective consideration of bias, fairness, accountability, and related ethical and social implications.Varsha D. BadalVarsha D. BadalCamille NebekerKaoru ShinkawaYasunori YamadaKelly E. RentscherHo-Cheol KimEllen E. LeeEllen E. LeeEllen E. LeeFrontiers Media S.A.articleartificial intelligencesocial connectednessgenderlonelinessNLPSocial supportPsychiatryRC435-571ENFrontiers in Psychiatry, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence social connectedness gender loneliness NLP Social support Psychiatry RC435-571
spellingShingle	artificial intelligence social connectedness gender loneliness NLP Social support Psychiatry RC435-571 Varsha D. Badal Varsha D. Badal Camille Nebeker Kaoru Shinkawa Yasunori Yamada Kelly E. Rentscher Ho-Cheol Kim Ellen E. Lee Ellen E. Lee Ellen E. Lee Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
description	Introduction: Social isolation and loneliness (SI/L) are growing problems with serious health implications for older adults, especially in light of the COVID-19 pandemic. We examined transcripts from semi-structured interviews with 97 older adults (mean age 83 years) to identify linguistic features of SI/L.Methods: Natural Language Processing (NLP) methods were used to identify relevant interview segments (responses to specific questions), extract the type and number of social contacts and linguistic features such as sentiment, parts-of-speech, and syntactic complexity. We examined: (1) associations of NLP-derived assessments of social relationships and linguistic features with validated self-report assessments of social support and loneliness; and (2) important linguistic features for detecting individuals with higher level of SI/L by using machine learning (ML) models.Results: NLP-derived assessments of social relationships were associated with self-reported assessments of social support and loneliness, though these associations were stronger in women than in men. Usage of first-person plural pronouns was negatively associated with loneliness in women and positively associated with emotional support in men. ML analysis using leave-one-out methodology showed good performance (F1 = 0.73, AUC = 0.75, specificity = 0.76, and sensitivity = 0.69) of the binary classification models in detecting individuals with higher level of SI/L. Comparable performance were also observed when classifying social and emotional support measures. Using ML models, we identified several linguistic features (including use of first-person plural pronouns, sentiment, sentence complexity, and sentence similarity) that most strongly predicted scores on scales for loneliness and social support.Discussion: Linguistic data can provide unique insights into SI/L among older adults beyond scale-based assessments, though there are consistent gender differences. Future research studies that incorporate diverse linguistic features as well as other behavioral data-streams may be better able to capture the complexity of social functioning in older adults and identification of target subpopulations for future interventions. Given the novelty, use of NLP should include prospective consideration of bias, fairness, accountability, and related ethical and social implications.
format	article
author	Varsha D. Badal Varsha D. Badal Camille Nebeker Kaoru Shinkawa Yasunori Yamada Kelly E. Rentscher Ho-Cheol Kim Ellen E. Lee Ellen E. Lee Ellen E. Lee
author_facet	Varsha D. Badal Varsha D. Badal Camille Nebeker Kaoru Shinkawa Yasunori Yamada Kelly E. Rentscher Ho-Cheol Kim Ellen E. Lee Ellen E. Lee Ellen E. Lee
author_sort	Varsha D. Badal
title	Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
title_short	Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
title_full	Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
title_fullStr	Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
title_full_unstemmed	Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing
title_sort	do words matter? detecting social isolation and loneliness in older adults using natural language processing
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/0da859c5faa443f9994bd6f6ffaa0946
work_keys_str_mv	AT varshadbadal dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT varshadbadal dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT camillenebeker dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT kaorushinkawa dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT yasunoriyamada dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT kellyerentscher dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT hocheolkim dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT ellenelee dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT ellenelee dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing AT ellenelee dowordsmatterdetectingsocialisolationandlonelinessinolderadultsusingnaturallanguageprocessing
_version_	1718426647869259776

Do Words Matter? Detecting Social Isolation and Loneliness in Older Adults Using Natural Language Processing

Ejemplares similares