Key language markers of depression on social media depend on race.

Depression has robust natural language correlates and can increasingly be measured in language using predictive models. However, despite evidence that language use varies as a function of individual demographic features (e.g., age, gender), previous work has not systematically examined whether and how depression's association with language varies by race. We examine how race moderates the relationship between language features (i.e., first-person pronouns and negative emotions) from social media posts and self-reported depression, in a matched sample of Black and White English speakers in the United States. Our findings reveal moderating effects of race: While depression severity predicts I-usage in White individuals, it does not in Black individuals. White individuals use more belongingness and self-deprecation-related negative emotions. Machine learning models trained on similar amounts of data to predict depression severity performed poorly when tested on Black individuals, even when they were trained exclusively using the language of Black individuals. In contrast, analogous models tested on White individuals performed relatively well. Our study reveals surprising race-based differences in the expression of depression in natural language and highlights the need to understand these effects better, especially before language-based models for detecting psychological phenomena are integrated into clinical practice.

Characterizing COVID-19 Content Posted to TikTok: Public Sentiment and Response During the First Phase of the COVID-19 Pandemic.

PURPOSE: The purpose of this study was to characterize COVID-19 content posted by users and disseminated via TikTok, a social media platform that has become known largely as an entertainment platform for viral video-sharing. We sought to capture how TikTok videos posted during the initial months of the COVID pandemic changed over time as cases accelerated. METHODS: This study is an observational analysis of sequential TikTok videos with #coronavirus from January to March 2020. Videos were independently coded to assess content (e.g., health relatedness, humor, fear, empathy), misinformation, and public sentiment. To assess engagement, we also codified how often videos were shared relative to their content. RESULTS: We coded 750 videos and approximately one in four videos tagged with #coronavirus featured health-related content such as featuring objects such as face masks, hand sanitizer, and other cleaning products. Most videos evoked "humor/parody," whereas 15% and 6% evoked "fear" and "empathy", respectively. TikTok videos posted in March 2020 had the largest number of shares and comments compared with January and February 2020. The proportion of shares and comments for "misleading and incorrect information" featured in videos was lower in March than in January and February 2020. There was no statistical difference between the share and comment counts of videos coded as "incorrect/incomplete" and "correct" over the entire time period. CONCLUSIONS: Analyzing readily available social media platforms, such as TikTok provides real-time insights into public views, frequency and types of misinformation, and norms toward COVID-19. Analyzing TikTok videos has the potential to be used to inform public health messaging and public health mitigation strategies.

Predicting Cardiovascular Risk Using Social Media Data: Performance Evaluation of Machine-Learning Models.

BACKGROUND: Current atherosclerotic cardiovascular disease (ASCVD) predictive models have limitations; thus, efforts are underway to improve the discriminatory power of ASCVD models. OBJECTIVE: We sought to evaluate the discriminatory power of social media posts to predict the 10-year risk for ASCVD as compared to that of pooled cohort risk equations (PCEs). METHODS: We consented patients receiving care in an urban academic emergency department to share access to their Facebook posts and electronic medical records (EMRs). We retrieved Facebook status updates up to 5 years prior to study enrollment for all consenting patients. We identified patients (N=181) without a prior history of coronary heart disease, an ASCVD score in their EMR, and more than 200 words in their Facebook posts. Using Facebook posts from these patients, we applied a machine-learning model to predict 10-year ASCVD risk scores. Using a machine-learning model and a psycholinguistic dictionary, Linguistic Inquiry and Word Count, we evaluated if language from posts alone could predict differences in risk scores and the association of certain words with risk categories, respectively. RESULTS: The machine-learning model predicted the 10-year ASCVD risk scores for the categories <5%, 5%-7.4%, 7.5%-9.9%, and ≥10% with area under the curve (AUC) values of 0.78, 0.57, 0.72, and 0.61, respectively. The machine-learning model distinguished between low risk (<10%) and high risk (>10%) with an AUC of 0.69. Additionally, the machine-learning model predicted the ASCVD risk score with Pearson r=0.26. Using Linguistic Inquiry and Word Count, patients with higher ASCVD scores were more likely to use words associated with sadness (r=0.32). CONCLUSIONS: Language used on social media can provide insights about an individual's ASCVD risk and inform approaches to risk modification.

Machine Learning for Phone-Based Relationship Estimation: The Need to Consider Population Heterogeneity.

Estimating the category and quality of interpersonal relationships from ubiquitous phone sensor data matters for studying mental well-being and social support. Prior work focused on using communication volume to estimate broad relationship categories, often with small samples. Here we contextualize communications by combining phone logs with demographic and location data to predict interpersonal relationship roles on a varied sample population using automated machine learning methods, producing better performance (F1 = 0.68) than using communication features alone (F1 = 0.62). We also explore the effect of age variation in the underlying training sample on interpersonal relationship prediction and find that models trained on younger subgroups, which is popular in the field via student participation and recruitment, generalize poorly to the wider population. Our results not only illustrate the value of using data across demographics, communication patterns and semantic locations for relationship prediction, but also underscore the importance of considering population heterogeneity in phone-based personal sensing studies.

Evaluating the predictability of medical conditions from social media posts.

We studied whether medical conditions across 21 broad categories were predictable from social media content across approximately 20 million words written by 999 consenting patients. Facebook language significantly improved upon the prediction accuracy of demographic variables for 18 of the 21 disease categories; it was particularly effective at predicting diabetes and mental health conditions including anxiety, depression and psychoses. Social media data are a quantifiable link into the otherwise elusive daily lives of patients, providing an avenue for study and assessment of behavioral and environmental disease risk factors. Analogous to the genome, social media data linked to medical diagnoses can be banked with patients' consent, and an encoding of social media language can be used as markers of disease risk, serve as a screening tool, and elucidate disease epidemiology. In what we believe to be the first report linking electronic medical record data with social media data from consenting patients, we identified that patients' Facebook status updates can predict many health conditions, suggesting opportunities to use social media data to determine disease onset or exacerbation and to conduct social media-based health interventions.