Studying expressions of loneliness in individuals using twitter: an observational study

Sharath Chandra Guntuku, Rachelle Schneider, Arthur Pelullo, Jami Young, Vivien Wong, Lyle Ungar, Daniel Polsky, Kevin G. Volpp, Raina Merchant

Research output: Contribution to journalArticle

Abstract

Objectives Loneliness is a major public health problem and an estimated 17% of adults aged 18-70 in the USA reported being lonely. We sought to characterise the (online) lives of people who mention the words 'lonely' or 'alone' in their Twitter timeline and correlate their posts with predictors of mental health. Setting and design From approximately 400 million tweets collected from Twitter in Pennsylvania, USA, between 2012 and 2016, we identified users whose Twitter posts contained the words 'lonely' or 'alone' and compared them to a control group matched by age, gender and period of posting. Using natural-language processing, we characterised the topics and diurnal patterns of users' posts, their association with linguistic markers of mental health and if language can predict manifestations of loneliness. The statistical analysis, data synthesis and model creation were conducted in 2018-2019. Primary outcome measures We evaluated counts of language features in the users with posts including the words lonely or alone compared with the control group. These language features were measured by (a) open-vocabulary topics, (b) Linguistic Inquiry Word Count (LIWC) lexicon, (c) linguistic markers of anger, depression and anxiety, and (d) temporal patterns and number of drug words. Using machine learning, we also evaluated if expressions of loneliness can be predicted in users' timelines, measured by area under curve (AUC). Results Twitter timelines of users (n=6202) with posts including the words lonely or alone were found to include themes about difficult interpersonal relationships, psychosomatic symptoms, substance use, wanting change, unhealthy eating and having troubles with sleep. Their posts were also associated with linguistic markers of anger, depression and anxiety. A random forest model predicted expressions of loneliness online with an AUC of 0.86. Conclusions Users' Twitter timelines with the words lonely or alone often include psychosocial features and can potentially have associations with how individuals express and experience loneliness. This can inform low-resource online assessment for high-risk individuals experiencing loneliness and interventions focused on addressing morbidities in this condition.

Original languageEnglish (US)
Article number030355
JournalBMJ open
Volume9
Issue number11
DOIs
StatePublished - Nov 1 2019
Externally publishedYes

Fingerprint

Loneliness
Observational Studies
Linguistics
Language
Anger
Area Under Curve
Mental Health
Anxiety
Natural Language Processing
Depression
Control Groups
Statistical Data Interpretation
Vocabulary
Sleep
Public Health
Eating
Outcome Assessment (Health Care)
Morbidity
TimeLine
Pharmaceutical Preparations

Keywords

  • loneliness mentions
  • mental health
  • natural language processing
  • social media
  • twitter

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Guntuku, S. C., Schneider, R., Pelullo, A., Young, J., Wong, V., Ungar, L., ... Merchant, R. (2019). Studying expressions of loneliness in individuals using twitter: an observational study. BMJ open, 9(11), [030355]. https://doi.org/10.1136/bmjopen-2019-030355

Studying expressions of loneliness in individuals using twitter : an observational study. / Guntuku, Sharath Chandra; Schneider, Rachelle; Pelullo, Arthur; Young, Jami; Wong, Vivien; Ungar, Lyle; Polsky, Daniel; Volpp, Kevin G.; Merchant, Raina.

In: BMJ open, Vol. 9, No. 11, 030355, 01.11.2019.

Research output: Contribution to journalArticle

Guntuku, SC, Schneider, R, Pelullo, A, Young, J, Wong, V, Ungar, L, Polsky, D, Volpp, KG & Merchant, R 2019, 'Studying expressions of loneliness in individuals using twitter: an observational study', BMJ open, vol. 9, no. 11, 030355. https://doi.org/10.1136/bmjopen-2019-030355
Guntuku SC, Schneider R, Pelullo A, Young J, Wong V, Ungar L et al. Studying expressions of loneliness in individuals using twitter: an observational study. BMJ open. 2019 Nov 1;9(11). 030355. https://doi.org/10.1136/bmjopen-2019-030355
Guntuku, Sharath Chandra ; Schneider, Rachelle ; Pelullo, Arthur ; Young, Jami ; Wong, Vivien ; Ungar, Lyle ; Polsky, Daniel ; Volpp, Kevin G. ; Merchant, Raina. / Studying expressions of loneliness in individuals using twitter : an observational study. In: BMJ open. 2019 ; Vol. 9, No. 11.
@article{fd7b3cc330c44779bcb2d6c422e4b4fc,
title = "Studying expressions of loneliness in individuals using twitter: an observational study",
abstract = "Objectives Loneliness is a major public health problem and an estimated 17{\%} of adults aged 18-70 in the USA reported being lonely. We sought to characterise the (online) lives of people who mention the words 'lonely' or 'alone' in their Twitter timeline and correlate their posts with predictors of mental health. Setting and design From approximately 400 million tweets collected from Twitter in Pennsylvania, USA, between 2012 and 2016, we identified users whose Twitter posts contained the words 'lonely' or 'alone' and compared them to a control group matched by age, gender and period of posting. Using natural-language processing, we characterised the topics and diurnal patterns of users' posts, their association with linguistic markers of mental health and if language can predict manifestations of loneliness. The statistical analysis, data synthesis and model creation were conducted in 2018-2019. Primary outcome measures We evaluated counts of language features in the users with posts including the words lonely or alone compared with the control group. These language features were measured by (a) open-vocabulary topics, (b) Linguistic Inquiry Word Count (LIWC) lexicon, (c) linguistic markers of anger, depression and anxiety, and (d) temporal patterns and number of drug words. Using machine learning, we also evaluated if expressions of loneliness can be predicted in users' timelines, measured by area under curve (AUC). Results Twitter timelines of users (n=6202) with posts including the words lonely or alone were found to include themes about difficult interpersonal relationships, psychosomatic symptoms, substance use, wanting change, unhealthy eating and having troubles with sleep. Their posts were also associated with linguistic markers of anger, depression and anxiety. A random forest model predicted expressions of loneliness online with an AUC of 0.86. Conclusions Users' Twitter timelines with the words lonely or alone often include psychosocial features and can potentially have associations with how individuals express and experience loneliness. This can inform low-resource online assessment for high-risk individuals experiencing loneliness and interventions focused on addressing morbidities in this condition.",
keywords = "loneliness mentions, mental health, natural language processing, social media, twitter",
author = "Guntuku, {Sharath Chandra} and Rachelle Schneider and Arthur Pelullo and Jami Young and Vivien Wong and Lyle Ungar and Daniel Polsky and Volpp, {Kevin G.} and Raina Merchant",
year = "2019",
month = "11",
day = "1",
doi = "10.1136/bmjopen-2019-030355",
language = "English (US)",
volume = "9",
journal = "BMJ Open",
issn = "2044-6055",
publisher = "BMJ Publishing Group",
number = "11",

}

TY - JOUR

T1 - Studying expressions of loneliness in individuals using twitter

T2 - an observational study

AU - Guntuku, Sharath Chandra

AU - Schneider, Rachelle

AU - Pelullo, Arthur

AU - Young, Jami

AU - Wong, Vivien

AU - Ungar, Lyle

AU - Polsky, Daniel

AU - Volpp, Kevin G.

AU - Merchant, Raina

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Objectives Loneliness is a major public health problem and an estimated 17% of adults aged 18-70 in the USA reported being lonely. We sought to characterise the (online) lives of people who mention the words 'lonely' or 'alone' in their Twitter timeline and correlate their posts with predictors of mental health. Setting and design From approximately 400 million tweets collected from Twitter in Pennsylvania, USA, between 2012 and 2016, we identified users whose Twitter posts contained the words 'lonely' or 'alone' and compared them to a control group matched by age, gender and period of posting. Using natural-language processing, we characterised the topics and diurnal patterns of users' posts, their association with linguistic markers of mental health and if language can predict manifestations of loneliness. The statistical analysis, data synthesis and model creation were conducted in 2018-2019. Primary outcome measures We evaluated counts of language features in the users with posts including the words lonely or alone compared with the control group. These language features were measured by (a) open-vocabulary topics, (b) Linguistic Inquiry Word Count (LIWC) lexicon, (c) linguistic markers of anger, depression and anxiety, and (d) temporal patterns and number of drug words. Using machine learning, we also evaluated if expressions of loneliness can be predicted in users' timelines, measured by area under curve (AUC). Results Twitter timelines of users (n=6202) with posts including the words lonely or alone were found to include themes about difficult interpersonal relationships, psychosomatic symptoms, substance use, wanting change, unhealthy eating and having troubles with sleep. Their posts were also associated with linguistic markers of anger, depression and anxiety. A random forest model predicted expressions of loneliness online with an AUC of 0.86. Conclusions Users' Twitter timelines with the words lonely or alone often include psychosocial features and can potentially have associations with how individuals express and experience loneliness. This can inform low-resource online assessment for high-risk individuals experiencing loneliness and interventions focused on addressing morbidities in this condition.

AB - Objectives Loneliness is a major public health problem and an estimated 17% of adults aged 18-70 in the USA reported being lonely. We sought to characterise the (online) lives of people who mention the words 'lonely' or 'alone' in their Twitter timeline and correlate their posts with predictors of mental health. Setting and design From approximately 400 million tweets collected from Twitter in Pennsylvania, USA, between 2012 and 2016, we identified users whose Twitter posts contained the words 'lonely' or 'alone' and compared them to a control group matched by age, gender and period of posting. Using natural-language processing, we characterised the topics and diurnal patterns of users' posts, their association with linguistic markers of mental health and if language can predict manifestations of loneliness. The statistical analysis, data synthesis and model creation were conducted in 2018-2019. Primary outcome measures We evaluated counts of language features in the users with posts including the words lonely or alone compared with the control group. These language features were measured by (a) open-vocabulary topics, (b) Linguistic Inquiry Word Count (LIWC) lexicon, (c) linguistic markers of anger, depression and anxiety, and (d) temporal patterns and number of drug words. Using machine learning, we also evaluated if expressions of loneliness can be predicted in users' timelines, measured by area under curve (AUC). Results Twitter timelines of users (n=6202) with posts including the words lonely or alone were found to include themes about difficult interpersonal relationships, psychosomatic symptoms, substance use, wanting change, unhealthy eating and having troubles with sleep. Their posts were also associated with linguistic markers of anger, depression and anxiety. A random forest model predicted expressions of loneliness online with an AUC of 0.86. Conclusions Users' Twitter timelines with the words lonely or alone often include psychosocial features and can potentially have associations with how individuals express and experience loneliness. This can inform low-resource online assessment for high-risk individuals experiencing loneliness and interventions focused on addressing morbidities in this condition.

KW - loneliness mentions

KW - mental health

KW - natural language processing

KW - social media

KW - twitter

UR - http://www.scopus.com/inward/record.url?scp=85074546314&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074546314&partnerID=8YFLogxK

U2 - 10.1136/bmjopen-2019-030355

DO - 10.1136/bmjopen-2019-030355

M3 - Article

C2 - 31685502

AN - SCOPUS:85074546314

VL - 9

JO - BMJ Open

JF - BMJ Open

SN - 2044-6055

IS - 11

M1 - 030355

ER -