Investigating Patient Attitudes Towards the use of Social Media
            Data to Augment Depression Diagnosis and Treatment: a Qualitative
            Study

Mikal, Jude P.; Hurst, Samantha; Conway, Mike

doi:10.18653/v1/w17-3105

Cited by 13 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the first two weeks of widespread of COVID-19 in the United States (3/8/2020–3/22/2020), we recruited individuals to participate in a weekly survey on social media use. Individuals were recruited via snowball sampling with announcements posted to several Facebook groups used in prior research studies ( Mikal et al, 2016 , 2017 , 2019 , 2020a , 2020b ).…”

Section: Methodsmentioning

confidence: 99%

Social media as a modern Emergency Broadcast System: A longitudinal qualitative study of social media during COVID-19 and its impacts on social connection and social distancing compliance

Mikal

Wurtz

2021

Computers in Human Behavior Reports

View full text Add to dashboard Cite

In the wake of COVID-19 social distancing recommendations, social media assumed a central - if unofficial - role in ensuring that individuals remained informed and connected throughout the pandemic. Yet while research shows that social media can be an effective platform for connecting individuals socially and fostering social support exchanges, both the platforms and the support exchanged therein have been mired in considerable controversies regarding their use as a tool for positive social engagement. The goal of this study is to qualitatively evaluate longitudinal changes to social media engagement during social distancing recommendations and orders to shelter-in-place. To do this, we collected longitudinal, qualitative survey data from a group of adults over the eight weeks during which most states had issued orders to shelter-in-place. We analyze data for evidence of social connection, stress reduction, and support exchange, and evaluate the impact of online social ties on staying informed and on compliance with CDC recommendations and shelter-in-place orders. Results showed a clear longitudinal evolution of users’ online social engagement. Early use was characterized by agentic purposeful engagement, information sharing, and community resource mobilization. However, over time these patterns gave way to more passive use characterized by listlessness, contentiousness and misinformation as the pandemic wore on in weeks. As social media comes to occupy an increasingly important role in the exchange of information (and misinformation) this study has important implications for the health of users and the role of social media in future disasters, including how social media impacts both stress and health related behaviors.

show abstract

Section: Methodsmentioning

confidence: 99%

Social media as a modern Emergency Broadcast System: A longitudinal qualitative study of social media during COVID-19 and its impacts on social connection and social distancing compliance

Mikal

Wurtz

2021

Computers in Human Behavior Reports

View full text Add to dashboard Cite

show abstract

“…Whether potential positive outcomes (e.g., development of systems for recommending mental health care, fiduciary aid to address population-level crises) offset these threats remains largely dependent on an individual's personal life experience. For example, psychiatric patients have expressed stronger approval toward analysis of their social media than members of the general public (Mikal et al, 2017). The same holds true amongst younger individuals (Naslund and Aschbrenner, 2019).…”

Section: Ethical Considerationsmentioning

confidence: 99%

Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses

Harrigian¹,

Dredze²

2022

Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology

View full text Add to dashboard Cite

Self-disclosed mental health diagnoses, which serve as ground truth annotations of mental health status in the absence of clinical measures, underpin the conclusions behind most computational studies of mental health language from the last decade. However, psychiatric conditions are dynamic; a prior depression diagnosis may no longer be indicative of an individual's mental health, either due to treatment or other mitigating factors. We ask: to what extent are self-disclosures of mental health diagnoses actually relevant over time? We analyze recent activity from individuals who disclosed a depression diagnosis on social media over five years ago and, in turn, acquire a new understanding of how presentations of mental health status on social media manifest longitudinally. We also provide expanded evidence for the presence of personality-related biases in datasets curated using self-disclosed diagnoses. Our findings motivate three practical recommendations for improving mental health datasets curated using self-disclosed diagnoses:1. Annotate diagnosis dates and psychiatric comorbidities 2. Sample control groups using propensity score matching 3. Identify and remove spurious correlations introduced by selection bias

show abstract

“…The authors of [9] used Natural Language Processing algorithms in order to analyse social media data to enhance mental health care. The investigation was based on secondary analysis of a series of five focus groups with Twitter users, including three groups consisting of participants with a self-reported history of depression, and two groups consisting of participants without a selfreported history of depression.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Techniques and Data Science Trends

2022

View full text Add to dashboard Cite

During the COVID-19 pandemic millions of people were affected due to quarantine and restrictions. With more than half of the world's population active on social media, people resorted to these platforms as their outlet for emotions. This led to researchers analysing content on social media to detect depression by studying the patterns of content posting. This paper focuses on finding a data-driven metric called 'Happiness Factor' of a user to assess their mental health. Various models were trained to classify a post as 'depressed'. A user's 'Happiness Factor' was calculated based on the nature of their posts. This metric identifies degrees of depression of a user. The results show the effectiveness of the classifier in identifying the depression level. Also, a Mental Health Awareness Resource System is proposed which recommends mental health awareness resources to users on their social media interface based on their 'Happiness Factor'.

show abstract

Investigating Patient Attitudes Towards the use of Social Media Data to Augment Depression Diagnosis and Treatment: a Qualitative Study

Cited by 13 publications

References 24 publications

Social media as a modern Emergency Broadcast System: A longitudinal qualitative study of social media during COVID-19 and its impacts on social connection and social distancing compliance

Social media as a modern Emergency Broadcast System: A longitudinal qualitative study of social media during COVID-19 and its impacts on social connection and social distancing compliance

Then and Now: Quantifying the Longitudinal Validity of Self-Disclosed Depression Diagnoses

Machine Learning Techniques and Data Science Trends

Contact Info

Product

Resources

About