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

Abstract

ObjectivesLoneliness 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 designFrom 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 measuresWe 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).ResultsTwitter 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.ConclusionsUsers’ 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.

Variability in Language used on Social Media prior to Hospital Visits

“…As a result, social media now provides a view into an enormous sector of patients' health that was previously unobservable. Statistical and machine learning language processing techniques have been used to relate social media language use to a wide variety of health-related outcomes including mood 3 and mental health attributes such as depression 4 , suicidal ideation 5,6 , loneliness 7 , and post-traumatic stress disorder 8 .…”

Public Priorities and Concerns Regarding COVID-19 in an Online Discussion Forum: Longitudinal Topic Modeling

“…5 For each of the 50 topics, we reviewed the ten words and comments most associated with each topic. 6 We identified topics that fell into three categories of interest: response to public health measures, impact on daily life, and sense of pandemic severity. We tracked daily variations in the average prevalence of topics across all comments.…”

How Health Care Workers Wield Influence Through Twitter Hashtags: Retrospective Cross-sectional Study of the Gun Violence and COVID-19 Public Health Crises

“…We note that the Twitter API limits such streams to 1% of the total Twitter volume at any given moment. Similar methods have been used in prior work studying health-related tweets [10][11][12][13][14].…”