Users who tweet about loneliness post could predict mental health concerns


Loneliness is estimated to affect roughly one in five adults in the United States. It also stands as a public health crisis because loneliness has been tied to depression, cardiovascular disease and dementia, among other conditions.

As such, a team of researchers at Penn Medicine came together to determine what topics and themes could be associated with loneliness by accessing content posted by users on Twitter.

By applying linguistic analytic models to tweets, the researchers found users who tweeted about loneliness post significantly more often about mental well-being concerns and things like struggles with relationships, substance use, and insomnia. F

indings from this work, published today in BMJ Open, could lead to easier identification of users who are lonely and providing support for them even if they don’t explicitly tweet about feeling alone.ants.

“Loneliness can be a slow killer, as some of the medical problems associated with it can take decades to manifest,” said the study’s lead author Sharath Chandra Guntuku, PhD, a research scientist in Penn Medicine’s Center for Digital Health.

“If we are able to identify lonely individuals and intervene before the health conditions associated with the themes we found begin to unfold, we have a change to help those much earlier in their lives. This could be very powerful and have long-lasting effects on public health.”

By determining typical themes and linguistic markers posted to social media that are associated with people who are lonely, the team has uncovered some of the ingredients necessary to construct a “loneliness prediction system.”

“Social media has the potential to allow researchers and clinicians to passively measure loneliness over time,” said study co-author Rachelle Schneider, a research coordinator in the Center for Digital Health. “Through validating our data, we can develop a reliable and accurate tool to do this monitoring.”

Focusing on Twitter users in Pennsylvania with publicly accessible accounts, the team found 6,202 who included words like “lonely” or “alone” more than five times over the period reviewed, which stretched from 2012 to 2016.

Comparing the entire Twitter timelines of these users to a matched group who did not have such language included their posts, the researchers showed that “lonely” users tweeted nearly twice as much and were much more likely to do so at night.

When the tweets were analyzed via several different linguistic analytic models, the users who posted about loneliness had an extremely high association with anger, depression, and anxiety, when compared to the “non-lonely” group.

Additionally, the lonely group were significantly associated with tweeting about struggles with relationships (for example, using phrases like “want somebody” or “no one to”), substance use (“smoke,” “weed,” and/or “drunk”) and issues with regulating their emotions (“I just wanna,” “I can’t,” and/or the use of expletives).

“On Twitter, we found lonely users expressing a need for social support, and it appears that the use of expletives and the expression of anger is a sign of that being unfulfilled,” Guntuku said. “Moving forward, we will need to test this in order to determine if one may cause the other – does loneliness cause anger, or vice versa?”

Users in the group that didn’t post about loneliness seemed to display some social connections, as they were found to be more likely to engage in conversations, especially by including others’ user names (using “@twitter_handle”) in their tweets.

The study’s senior author Raina Merchant, MD, the director of the Center for Digital Health, explained that once loneliness is identified, it can be addressed in a number of ways.

By determining typical themes and linguistic markers posted to social media that are associated with people who are lonely, the team has uncovered some of the ingredients necessary to construct a “loneliness prediction system.”

“It’s clear that there isn’t a one-size-fits-all model,” she said. “Some interventions include buddy systems, peer-to-peer networks, therapy, and skill development for navigating day-to-day interactions with others.”

In the future, the researchers hope to develop a better measure of the different dimensions of loneliness that online users are feeling and expressing. Guntuku said that early work is showing that a predictive model they developed as a result of this study is accurately predicting loneliness in a patient population that opted-in to share their Twitter data and took a validated loneliness survey.

The hope is to soon launch an initiative that identifies lonely patients receiving care in the hospital and then to develop interventions for them and their families/support systems.

Funding: The study was funded, in part, by the Pennsylvania Department of Health (grant number 4290-567862-2446-2049).

Other authors on this study include Arthur Pelullo, Jami F. Young, Vivien Wong, Lyle H. Ungar, Daniel Polsky, and Kevin Volpp

Mental health is an essential component of our health.

The World Health Organization (WHO) defines mental health as a “state of well-being in which people realize their potential, cope with the normal stresses of life, work productively, and contribute to their communities” [1].

Good mental health is about being cognitive, emotionally and socially healthy and it helps to determine the way we think and feel, in relation with others and how we make choices. Several factors, such as genetic, sociocultural, economic, political and environmental aspects, shape and influence our mental health.

In the last few years, mental disorders have become a major concern in public health, and they are one of the main causes of the overall disease burden worldwide.

They have devastating consequences for both patients and their families [27].

According to the WHO, depressive disorders are the most common among the mental illnesses [8]. Such disorders conditions are characterized by sadness, loss of interest and pleasure, feelings of guilt or low self-worth, disturbed sleep or appetite, feelings of tiredness, and poor concentration [8].

In 2018, at the global level, more than 300 million people were suffering from depression, and it is the main contributor to global disability. Depression has several consequences, both personal and social costs [9,10].

In some cases, depression can lead to suicide ideation and attempts [2,11].

The prevalence of this disorder changes depending on age, but it affects the whole population, from children and adolescents to elderly people. From 2005 to 2015, the number of people with depression increased by around 18% [12].

In this context, social media platforms allow to observe the activities, thoughts, and feelings of people’s daily lives and thereby investigate their emotional well-being. This domain has become a new growing area of interest in public health and health care research [1316].

People with depression often use social media to talk about their illness and treatment, share information and experiences, seek social support and advice, reduce social isolation, and manage their mental illness [1521].

In addition, access to mobile devices facilitates the use of social media platforms, such as Twitter and Facebook, at any time and at any place. Social media, such as Twitter, is by nature social, and we can consequently find social patterns in Twitter feeds, thereby revealing key aspects of mental and affective disorders [22].

Social media has become an important source of health-related information, which allows us to detect and predict affective disorders and which can be used as an additional tool for mental health monitoring and infoveillance [2326].

Furthermore, the application of different methodologies based on natural language processing and machine learning technologies has proved to be effective in supporting and automating the identification of early signs of mental illness by analyzing the content shared on the Web by individuals [1315,27].

This human interaction with social media contributes to build the so-called digital phenotype, reshaping disease expression in terms of the lived experience of individuals and detecting early manifestations of several conditions [28].

Twitter is an internet microblogging social media service that allows users to post short messages about facts, feelings and opinions, and, as shown in previous studies, users’ health conditions [15].

Twitter is one of the most important social media platforms in terms of number of users, with more than 330 million active users worldwide [29].

Since November 2017, the maximum number of characters of a tweet has been increased from 140 to 280. By analyzing huge amounts of text, researchers can link everyday language use with social behavior and personality [30,31].

Language, as a means of communication, constitutes an essential element for providing valuable insights about people’s interests, feelings and concerns [32].

For this reason, the analysis of the messages posted on social media platforms may provide information about many personality traits, lifestyles, and psychological disorders [13,33,34].

The potential anonymity of social media encourages its users to be more willing to report health information, such as details of their mental disorders and treatments received. In addition, it is seen as a way to communicate and receive support from others with similar experiences, avoiding the isolation and fighting the social stigma of these conditions [12,15,17,19,32,35].

Nevertheless, users suffering from depression may also feel uncomfortable socializing and consuming information on social media platforms [36]. Several features of the messages, such as number and frequency of tweets, distribution throughout the day or during the night hours, and their seasonal character, can be used for the detection and monitoring of mental disorders, such as depression [20].

This knowledge can help health care professionals and health institutions and services in the decision-making processes to ensure better management of patients suffering from depression.

University of Pennsylvania
Media Contacts:
Frank Otto – University of Pennsylvania
Image Source:
The image is in the public domain.

Original Research: Open access
“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.
BMJ Open doi:10.1136/bmjopen-2019-030355.


Please enter your comment!
Please enter your name here

Questo sito usa Akismet per ridurre lo spam. Scopri come i tuoi dati vengono elaborati.