ABSTRACT
BACKGROUND: The COVID-19 pandemic has placed strains on communities. During this public health crisis, health systems have created remote methods of monitoring symptom progression and delivering care virtually. OBJECTIVE: Using an SMS text message-based system, we sought to build and test a remote model to explore community needs, connect individuals to curated resources, and facilitate community health worker intervention when needed during the pandemic. The primary aims of this pilot study were to establish the feasibility (ie, engagement with the text line) and acceptability (ie, participant ratings of resources and service) of delivering automated well-being resources via smartphone technology. METHODS: Eligible patients (aged 18 years or older, having a cell phone with SMS text messaging capability, and recently visited the emergency department) were identified using the electronic health record. The patients were consented to enroll and begin receiving COVID-19-related information and links to community resources. We collected open-ended and close-ended resource and mood ratings. We calculated the frequencies and conducted a thematic review of the open-ended responses. RESULTS: In 7 weeks, 356 participants were enrolled; 13,917 messages were exchanged including 333 resource ratings (mean 4) and 673 well-being scores (mean 6.8). We received and coded 386 open-ended responses, most of which elaborated upon their self-reported mood score (29%). Overall, 77% (n=274) of our participants rated the platform as a service they would highly recommend to a family member or friend. CONCLUSIONS: This approach is designed to broaden the reach of health systems, tailor to community needs in real time, and connect at-risk individuals with robust community health support.
ABSTRACT
BACKGROUND: COVID-19 continues to disrupt global health and well-being. In April-May 2020, we generated a digital, remote interactive tool to provide health and well-being resources and foster connectivity among community members through a text messaging platform. OBJECTIVE: This study aimed to prospectively investigate the ability of a health system-based digital, remote, interactive tool to provide health and well-being resources to local community participants and to foster connectivity among them during the early phases of COVID-19. METHODS: We performed descriptive and nonparametric longitudinal statistical analyses to describe and compare the participants' mood ratings over time and thematic analysis of their responses to text messages to further assess mood. RESULTS: From among 393 individuals seeking care in an urban emergency department in an academic setting, engaged in a two-way text messaging platform, we recorded 287 mood ratings and 368 qualitative responses. We observed no difference in the initial mood rating by week of enrollment [Kruskal-Wallis chi-square H(5)=1.34; P=.93], and the average mood rating did not change for participants taken together [Friedman chi-square Q(3)=0.32; P=.96]. However, of participants providing mood ratings at baseline, mood improved significantly among participants who reported a low mood rating at baseline [n=25, 14.97%; Q(3)=20.68; P<.001] but remained stable among those who reported a high mood rating at baseline [n=142, 85.03%; Q(3)=2.84; P=.42]. Positive mood elaborations most frequently included words related to sentiments of thankfulness and gratitude, mostly for a sense of connection and communication; in contrast, negative mood elaborations most frequently included words related to anxiety. CONCLUSIONS: Our findings suggest the feasibility of engaging individuals in a digital community with an emergency department facilitation. Specifically, for those who opt to engage in a text messaging platform during COVID-19, it is feasible to assess and respond to mood-related queries with vetted health and well-being resources.
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.
