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 Responses to COVID-19 Vaccine Promotion on TikTok.

PURPOSE: The Alabama Department of Public Health (ADPH) sponsored a TikTok contest to improve vaccination rates among young people. This analysis sought to advance understanding of COVID-19 vaccine perceptions among ADPH contestants and TikTok commenters. APPROACH: This exploratory content analysis characterized sentiment and imagery in the TikTok videos and comments. Videos were coded by two reviewers and engagement metrics were collected for each video. SETTING: Publicly available TikTok videos entered into ADPH's contest with the hashtags #getvaccinatedAL and #ADPH between July 16 - August 6, 2021. PARTICIPANTS: ADPH contestants (n = 44) and TikTok comments (n = 502). METHOD: A content analysis was conducted; videos were coded by two reviewers and engagement metrics was collected for each video (e.g., reason for vaccination, content, type of vaccination received). Video comments were analyzed using VADER, a lexicon and rule-based sentiment analysis tool). RESULTS: Of 44 videos tagged with #getvaccinatedAL and #ADPH, 37 were related to the contest. Of the 37 videos, most cited family/friends and civic duty as their reason to get the COVID-19 vaccine. Videos were shared an average of 9 times and viewed 977 times. 70% of videos had comments, ranging from 0-61 (mean 44). Words used most in positively coded comments included, "beautiful," "smiling face emoji with 3 hearts," "masks," and "good.;" whereas words used most in negatively coded comments included "baby," "me," "chips," and "cold." CONCLUSION: Understanding COVID-19 vaccine sentiment expressed on social media platforms like TikTok can be a powerful tool and resource for public health messaging.