Mental Health Surveillance over Social Media with Digital Cohorts

@article{Amir2019MentalHS,
  title={Mental Health Surveillance over Social Media with Digital Cohorts},
  author={Silvio Amir and Mark Dredze and John W. Ayers},
  journal={Proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology},
  year={2019}
}
The ability to track mental health conditions via social media opened the doors for large-scale, automated, mental health surveillance. However, inferring accurate population-level trends requires representative samples of the underlying population, which can be challenging given the biases inherent in social media data. While previous work has adjusted samples based on demographic estimates, the populations were selected based on specific outcomes, e.g. specific mental health conditions. We… 

Figures from this paper

Towards Understanding the Role of Gender in Deploying Social Media-Based Mental Health Surveillance Models
Spurred by advances in machine learning and natural language processing, developing social media-based mental health surveillance models has received substantial recent attention. For these models to
Gender and Racial Fairness in Depression Research using Social Media
TLDR
This study analyzes the fairness of depression classifiers trained on Twitter data with respect to gender and racial demographic groups to find that model performance differs for underrepresented groups, and investigates sources of these biases beyond data representation.
Do Models of Mental Health Based on Social Media Data Generalize?
TLDR
It is revealed that substantial loss occurs when transferring between platforms, but also that there exist several unreliable confounding factors that may enable researchers to overestimate classification performance.
Automatic gender detection in Twitter profiles for health-related cohort studies
TLDR
The authors' publicly available, automated gender detection pipeline may aid cohort-specific social media data analyses and illustrate how gender information can be incorporated into a social media-based health-related study.
Qualitative Analysis of Depression Models by Demographics
Models for identifying depression using social media text exhibit biases towards different gender and racial/ethnic groups. Factors like representation and balance of groups within the dataset are
Automatic Gender Detection in Twitter Profiles for Health-related Cohort Studies
TLDR
The authors' publicly-available, automated gender detection pipeline may aid cohort-specific social media data analyses and illustrate how gender information can be incorporated into a SM-based health-related study.
Using Noisy Self-Reports to Predict Twitter User Demographics
TLDR
A method to identify self-reports of race and ethnicity from Twitter profile descriptions is presented, and self-report datasets enable improvements in classification performance on gold standard self- report survey data.
A Psychologically Informed Part-of-Speech Analysis of Depression in Social Media
TLDR
An extensive part-of-speech analysis of the discourse of social media users with depression, providing insights regarding the way in which depressed individuals are expressing themselves on social media platforms, allowing for better-informed computational models to help monitor and prevent mental illnesses.
Health Misinformation in Search and Social Media
TLDR
It is suggested that there is a potential for people to be harmed by search engine results and a high precision approach to track misinformation in social media is successfully built.
Demographic Representation and Collective Storytelling in the Me Too Twitter Hashtag Activism Movement
TLDR
It was found that tweets authored by white women were overrepresented in the movement compared to other demographics, aligning with criticism of unequal representation and the implications of this work for digital activism research and design are discussed.
...
1
2
...

References

SHOWING 1-10 OF 33 REFERENCES
Quantifying Mental Health Signals in Twitter
TLDR
A novel method for gathering data for a range of mental illnesses quickly and cheaply is presented, then analysis of four in particular: post-traumatic stress disorder, depression, bipolar disorder, and seasonal affective disorder are focused on.
Using Matched Samples to Estimate the Effects of Exercise on Mental Health via Twitter
TLDR
This work trains a text classifier to estimate the volume of a user's tweets expressing anxiety, depression, or anger, and finds that those who exercise regularly have significantly fewer tweets expressing depression or anxiety; there is no significant difference in rates of tweets expressing anger.
Measuring Post Traumatic Stress Disorder in Twitter
TLDR
PTSD is considered, a serious condition that affects millions worldwide, with especially high rates in military veterans, and its utility is demonstrated by examining differences in language use between PTSD and random individuals, building classifiers to separate these two groups and by detecting elevated rates of PTSD at and around U.S. military bases using classifiers.
Social Monitoring for Public Health
TLDR
This book presents an overview of the progress on uses of social monitoring to study public health over the past decade, and explains available data sources, common methods, and survey research on social monitoring in a wide range of public health areas.
Quantifying Mental Health from Social Media with Neural User Embeddings
TLDR
This paper estimates user embeddings for a set of users known to be affected by depression and post-traumatic stress disorder, and assesses the performance of downstream mental health prediction models based on these features.
From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses
TLDR
A broad range of mental health conditions in Twitter data is examined by identifying self-reported statements of diagnosis and language differences between ten conditions with respect to the general population, and to each other are systematically explored.
Detection of User Demographics on Social Media: A Review of Methods and Recommendations for Best Practices
TLDR
This work seeks to provide a review of existing approaches to automated detection of demographic characteristics of social media users, and addresses the applicability of these methods to public health research; focusing on the challenge of working with highly dynamical, large scale data to study health trends.
Examining Patterns of Influenza Vaccination in Social Media
TLDR
This study builds and employs several natural language classifiers to examine and analyze behavioral patterns regarding influenza vaccination in Twitter across three dimensions: temporality (by week and month), geography (by US region), and demography (by gender).
Seasonality in seeking mental health information on Google.
TLDR
These are the first data published on patterns of seasonality in information seeking encompassing all the major mental illnesses, notable also because they likely would have gone undetected using traditional surveillance.
You Are What You Tweet: Analyzing Twitter for Public Health
TLDR
This work applies the recently introduced Ailment Topic Aspect Model to over one and a half million health related tweets and discovers mentions of over a dozen ailments, including allergies, obesity and insomnia, suggesting that Twitter has broad applicability for public health research.
...
1
2
3
4
...