Identifying self-disclosed anxiety on Twitter: A natural language processing approach.
Anxiety
Cyber-phenotype
Digital footprint
Natural language processing
Sentiment analysis
Twitter
Journal
Psychiatry research
ISSN: 1872-7123
Titre abrégé: Psychiatry Res
Pays: Ireland
ID NLM: 7911385
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
received:
01
12
2022
revised:
13
09
2023
accepted:
27
10
2023
medline:
6
12
2023
pubmed:
14
11
2023
entrez:
13
11
2023
Statut:
ppublish
Résumé
Text analyses of social media posts are a promising source of mental health information. This study used natural language processing to explore distinct language patterns on Twitter related to self-reported anxiety diagnosis. A total of 233.000 tweets made by 605 users (300 reporting anxiety diagnosis and 305 not) over six months were comparatively analysed, considering user behavior, Linguistic Inquiry Word Count (LIWC), and sentiment analysis. Twitter users with a self-disclosed diagnosis of anxiety were classified as 'anxious' to facilitate group comparisons. Supervised machine learning models showed a high prediction accuracy (Naïve Bayes 81.1 %, Random Forests 79.8 %, and LASSO-regression 79.4 %) in identifying Twitter users' self-disclosed diagnosis of anxiety. Additionally, a Latent Profile Analysis (LPA) identified four profiles characterized by high sentiment (31 % anxious participants), low sentiment (68 % anxious), self-immersed (80 % anxious), and normative behavior (38 % anxious). The digital footprint of self-disclosed anxiety on Twitter posts presented a high frequency of words conveying either negative sentiment, a low frequency of positive sentiment, a reduced frequency of posting, and lengthier texts. These distinct patterns enabled highly accurate prediction of anxiety diagnosis. On this basis, appropriately resourced, awareness raising, online mental health campaigns are advocated.
Sections du résumé
BACKGROUND
BACKGROUND
Text analyses of social media posts are a promising source of mental health information. This study used natural language processing to explore distinct language patterns on Twitter related to self-reported anxiety diagnosis.
METHODS
METHODS
A total of 233.000 tweets made by 605 users (300 reporting anxiety diagnosis and 305 not) over six months were comparatively analysed, considering user behavior, Linguistic Inquiry Word Count (LIWC), and sentiment analysis. Twitter users with a self-disclosed diagnosis of anxiety were classified as 'anxious' to facilitate group comparisons.
RESULTS
RESULTS
Supervised machine learning models showed a high prediction accuracy (Naïve Bayes 81.1 %, Random Forests 79.8 %, and LASSO-regression 79.4 %) in identifying Twitter users' self-disclosed diagnosis of anxiety. Additionally, a Latent Profile Analysis (LPA) identified four profiles characterized by high sentiment (31 % anxious participants), low sentiment (68 % anxious), self-immersed (80 % anxious), and normative behavior (38 % anxious).
CONCLUSION
CONCLUSIONS
The digital footprint of self-disclosed anxiety on Twitter posts presented a high frequency of words conveying either negative sentiment, a low frequency of positive sentiment, a reduced frequency of posting, and lengthier texts. These distinct patterns enabled highly accurate prediction of anxiety diagnosis. On this basis, appropriately resourced, awareness raising, online mental health campaigns are advocated.
Identifiants
pubmed: 37956589
pii: S0165-1781(23)00529-2
doi: 10.1016/j.psychres.2023.115579
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
115579Informations de copyright
Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.
Déclaration de conflit d'intérêts
Declaration of Competing Interest The authors of the present study do not report any conflict of interest.