Strategies for Identifying and Recruiting Women at High Risk for Breast Cancer for Research Outside of Clinical Settings: Observational Study.

BACKGROUND: Research is needed to understand and address barriers to risk management for women at high (≥20% lifetime) risk for breast cancer, but recruiting this population for research studies is challenging. OBJECTIVE: This paper compares a variety of recruitment strategies used for a cross-sectional, observational study of high-risk women. METHODS: Eligible participants were assigned female at birth, aged 25-85 years, English-speaking, living in the United States, and at high risk for breast cancer as defined by the American College of Radiology. Individuals were excluded if they had a personal history of breast cancer, prior bilateral mastectomy, medical contraindications for magnetic resonance imaging, or were not up-to-date on screening mammography per American College of Radiology guidelines. Participants were recruited from August 2020 to January 2021 using the following mechanisms: targeted Facebook advertisements, Twitter posts, ResearchMatch (a web-based research recruitment database), community partner promotions, paper flyers, and community outreach events. Interested individuals were directed to a secure website with eligibility screening questions. Participants self-reported method of recruitment during the eligibility screening. For each recruitment strategy, we calculated the rate of eligible respondents and completed surveys, costs per eligible participant, and participant demographics. RESULTS: We received 1566 unique responses to the eligibility screener. Participants most often reported recruitment via Facebook advertisements (724/1566, 46%) and ResearchMatch (646/1566, 41%). Community partner promotions resulted in the highest proportion of eligible respondents (24/46, 52%), while ResearchMatch had the lowest proportion of eligible respondents (73/646, 11%). Word of mouth was the most cost-effective recruitment strategy (US $4.66 per completed survey response) and paper flyers were the least cost-effective (US $1448.13 per completed survey response). The demographic characteristics of eligible respondents varied by recruitment strategy: Twitter posts and community outreach events resulted in the highest proportion of Hispanic or Latina women (1/4, 25% and 2/6, 33%, respectively), and community partner promotions resulted in the highest proportion of non-Hispanic Black women (4/24, 17%). CONCLUSIONS: Although recruitment strategies varied in their yield of study participants, results overall support the feasibility of identifying and recruiting women at high risk for breast cancer outside of clinical settings. Researchers must balance the associated costs and participant yield of various recruitment strategies in planning future studies focused on high-risk women.

Exploring arteriovenous malformations patient sentiments through 1401 social media posts.

INTRODUCTION: Social media has allowed patients with rare diseases to connect and discuss their experiences with others online. This study analyzed various social media platforms to better understand the patient's perception of arteriovenous malformation. METHODS: Twitter, Instagram, and TikTok were searched to find posts about patients' experiences with arteriovenous malformations (AVM). Posts unrelated to the patient's experience were excluded. Posts were coded for the relevant themes related to their experience with the disease, as well as engagement, and gender. RESULTS: The most common theme was raising awareness about the condition (87.0%). Recounting symptoms (50.2%), spreading positivity (17.5%), and survival (8.3%) were other common themes. Other prevalent themes were pain (5.2%) and fear of a rare disease (3.5%). Approximately half of AVM-related Instagram (47.93%) and TikTok (52.94%) posts raised awareness about the condition. Most Instagram (67.75%) and TikTok (89.71%) posts focused on recovery and rehabilitation. Most TikTok posts discussed "survival" or "death" (57.35%), while the majority focused on spreading positivity (79.41%). Most posts were made by women (69.6%). Females were more likely than males to post about the scientific explanation of AVMs (p = 0.003). CONCLUSION: Social media allows patients across the country and the globe to discuss their experiences with uncommon diseases and connect with others. It also allows AVM patients to share their experiences with other patients and the public.

From Tweets to Streets: Observational Study on the Association Between Twitter Sentiment and Anti-Asian Hate Crimes in New York City from 2019 to 2022.

BACKGROUND: Anti-Asian hate crimes escalated during the COVID-19 pandemic; however, limited research has explored the association between social media sentiment and hate crimes toward Asian communities. OBJECTIVE: This study aims to investigate the relationship between Twitter (rebranded as X) sentiment data and the occurrence of anti-Asian hate crimes in New York City from 2019 to 2022, a period encompassing both before and during COVID-19 pandemic conditions. METHODS: We used a hate crime dataset from the New York City Police Department. This dataset included detailed information on the occurrence of anti-Asian hate crimes at the police precinct level from 2019 to 2022. We used Twitter's application programming interface for Academic Research to collect a random 1% sample of publicly available Twitter data in New York State, including New York City, that included 1 or more of the selected Asian-related keywords and applied support vector machine to classify sentiment. We measured sentiment toward the Asian community using the rates of negative and positive sentiment expressed in tweets at the monthly level (N=48). We used negative binomial models to explore the associations between sentiment levels and the number of anti-Asian hate crimes in the same month. We further adjusted our models for confounders such as the unemployment rate and the emergence of the COVID-19 pandemic. As sensitivity analyses, we used distributed lag models to capture 1- to 2-month lag times. RESULTS: A point increase of 1% in negative sentiment rate toward the Asian community in the same month was associated with a 24% increase (incidence rate ratio [IRR] 1.24; 95% CI 1.07-1.44; P=.005) in the number of anti-Asian hate crimes. The association was slightly attenuated after adjusting for unemployment and COVID-19 emergence (ie, after March 2020; P=.008). The positive sentiment toward Asian tweets with a 0-month lag was associated with a 12% decrease (IRR 0.88; 95% CI 0.79-0.97; P=.002) in expected anti-Asian hate crimes in the same month, but the relationship was no longer significant after adjusting for the unemployment rate and the emergence of COVID-19 pandemic (P=.11). CONCLUSIONS: A higher negative sentiment level was associated with more hate crimes specifically targeting the Asian community in the same month. The findings highlight the importance of monitoring public sentiment to predict and potentially mitigate hate crimes against Asian individuals.

Sharing endodontic research on social media platforms: Is it effective? A 10-year timeline analysis.

The purpose of this study was to analyse the social media activity related to endodontic research over the last 10-years. All research articles published in endodontic journals listed in Scopus (Sc) published in 2012 and 2018 were included in our study. The Altmetric Attention Score (AAS), Twitter, and Facebook mentions were obtained for each article. Citation counts were extracted using two citation metrics: Google Scholar (GS) and Sc. Correlations between the AAS, the number of social media mentions, and citations were analysed using Spearman's rank order correlation coefficient. A multivariable Poisson log-linear regression analysis shows that papers mentioned on social media gain about 35% more citations in GS and 31% more citations in Sc. The academic citations per article on GS and Sc were positively correlated with the AAS. Our data suggest an increasing positive correlation between social media mentions and article citations over the years.

From Optional to Default　- Enhancing Article Viewership Through X (Formerly Twitter) Posting.

Background: The influence of a change to a default X summary posting strategy on article viewership has not been investigated. Methods and Results: We conducted a retrospective analysis of X-posting rates and journal viewership data for both the Circulation Journal and Circulation Reports from April 2022 to September 2023. Following protocol modifications in March 2023, there was a notable increase in the X-posting rate from 12.4% to 61.7%, along with an uptick in median access counts to article pages within 30 days, from 175 to 231.5. Conclusions: Trend analysis of journal viewership after a default X-posting strategy revealed an increase in viewer access.

Mental health and exercise during the COVID-19 pandemic: A Twitter sentiment analysis.

Beyond its immediate health consequences, the COVID-19 pandemic led to an exacerbation in the mental health of the global population. Regular exercise and its lack thereof are also known to affect mental health. Tweets and their content analysis can provide information about aspects of users' lives including their health habits and mental health. The purpose of this study was to examine individuals' exercise habits and mental health during the pandemic by means of sentiment and correlational analyses. These results indicate that, while exercise and mental health tweets were more COVID-focused in the first 12 months of the pandemic, exercise tweets became more exercise-focused, and mental health tweets became more mental-health-focused eventually during the pandemic. Efforts to increase exercise participation in individuals may prove beneficial. Further research needs to examine the effects of exercise on mental health in the aftermath of COVID-19.

The power of social media: broader Twitter outreach and higher Altmetric scores significantly amplify neurosurgical citation reach.

OBJECTIVE: The authors sought to quantify the role of social media-related academic activity through use of the Altmetric score (a composite score based on social media attention from a variety of sources) and investigate its potential impact on the number of citations received at 3 years postpublication (articles published between January 2019 and December 2019). METHODS: Articles published in the top 12 neurosurgical journals according to Google Scholar (based on 5-year Web of Science impact factors, 2017-2021) were identified. Data collected included days since publication, Altmetric scores, and total number of tweets (posts), and 3-year citations were obtained from Google Scholar. A multiple linear regression model was created that featured a blocking method to stratify confounding variables from most to least contributing. Furthermore, the data were dichotomized by publications with ≥ 10 citations (top 25th percentile) and those with < 10 to analyze the impact of the score on total number of citations received at 3 years, using an independent-samples Mann-Whitney U-test. RESULTS: Among 6721 included articles, the mean Altmetric score was 3.76 ± 15.69 and the mean number of citations received was 9.61 ± 22.16. When accounting for relevant control variables, the Altmetric score was a significant predictor of the total number of citations accumulated at 3 years (variability of 10.17%). On statistical testing, the Altmetric score was significantly higher in publications with ≥ 10 citations (p < 0.001). CONCLUSIONS: The authors report a strong, statistically significant correlation between the Altmetric score and the number of citations received. To their knowledge, this is the first study to demonstrate the impact of social media academic activity on neurosurgery article citation dissemination, potentially influencing resident medical education.

COVIDHealth: A novel labeled dataset and machine learning-based web application for classifying COVID-19 discourses on Twitter.

The COVID-19 pandemic has sparked widespread health-related discussions on social media platforms like Twitter (now named 'X'). However, the lack of labeled Twitter data poses significant challenges for theme-based classification and tweet aggregation. To address this gap, we developed a machine learning-based web application that automatically classifies COVID-19 discourses into five categories: health risks, prevention, symptoms, transmission, and treatment. We collected and labeled 6,667 COVID-19-related tweets using the Twitter API, and applied various feature extraction methods to extract relevant features. We then compared the performance of seven classical machine learning algorithms (Decision Tree, Random Forest, Stochastic Gradient Descent, Adaboost, K-Nearest Neighbor, Logistic Regression, and Linear SVC) and four deep learning techniques (LSTM, CNN, RNN, and BERT) for classification. Our results show that the CNN achieved the highest precision (90.41%), recall (90.4%), F1 score (90.4%), and accuracy (90.4%). The Linear SVC algorithm exhibited the highest precision (85.71%), recall (86.94%), and F1 score (86.13%) among classical machine learning approaches. Our study advances the field of health-related data analysis and classification, and offers a publicly accessible web-based tool for public health researchers and practitioners. This tool has the potential to support addressing public health challenges and enhancing awareness during pandemics. The dataset and application are accessible at https://github.com/Bishal16/COVID19-Health-Related-Data-Classification-Website.

Identifying Medicine Shortages With the Twitter Social Network: Retrospective Observational Study.

BACKGROUND: Early identification is critical for mitigating the impact of medicine shortages on patients. The internet, specifically social media, is an emerging source of health data. OBJECTIVE: This study aimed to explore whether a routine analysis of data from the Twitter social network can detect signals of a medicine shortage and serve as an early warning system and, if so, for which medicines or patient groups. METHODS: Medicine shortages between January 31 and December 1, 2019, were collected from the Dutch pharmacists' society's national catalog Royal Dutch Pharmacists Association (KNMP) Farmanco. Posts on these shortages were collected by searching for the name, the active pharmaceutical ingredient, or the first word of the brand name of the medicines in shortage. Posts were then selected based on relevant keywords that potentially indicated a shortage and the percentage of shortages with at least 1 post was calculated. The first posts per shortage were analyzed for their timing (median number of days, including the IQR) versus the national catalog, also stratified by disease and medicine characteristics. The content of the first post per shortage was analyzed descriptively for its reporting stakeholder and the nature of the post. RESULTS: Of the 341 medicine shortages, 102 (29.9%) were mentioned on Twitter. Of these 102 shortages, 18 (5.3% of the total) were mentioned prior to or simultaneous to publication by KNMP Farmanco. Only 4 (1.2%) of these were mentioned on Twitter more than 14 days before. On average, posts were published with a median delay of 37 (IQR 7-81) days to publication by KNMP Farmanco. Shortages mentioned on Twitter affected a greater number of patients and lasted longer than those that were not mentioned. We could not conclusively relate either the presence or absence on Twitter to a disease area or route of administration of the medicine in shortage. The first posts on the 102 shortages were mainly published by patients (n=51, 50.0%) and health care professionals (n=46, 45.1%). We identified 8 categories of nature of content. Sharing personal experience (n=44, 43.1%) was the most common category. CONCLUSIONS: The Twitter social network is not a suitable early warning system for medicine shortages. Twitter primarily echoes already-known information rather than spreads new information. However, Twitter or potentially any other social media platform provides the opportunity for future qualitative research in the increasingly important field of medicine shortages that investigates how a larger population of patients is affected by shortages.

Using Natural Language Processing on Expert Panel Discussions to Gain Insights for Recruitment, Retention and Intervention Adherence for Online Social Support Interventions on a Stage II-III Clinical Trial Among Hispanic and African American Dementia Caregivers.

We applied natural language processing (NLP) to a corpus extracted from 4 hours of expert panel discussion transcripts to determine the sustainability of a Stage II-III clinical trial of online social support interventions for Hispanic and African American dementia caregivers. Prominent topics included Technology/hard to reach populations, Training younger populations, Building trust, Privacy and security issues, Simplification of screening questions and recruitment procedures, Understanding participants' needs, Planning strategies and logistics, Potential recruitment places, Adjusting intervention size downwards to engage elderly participants, Targeting different generations, Internet-based interventions by age range, and Providing step-by-step instructions and an overview of the entire research process during recruitment. The application of NLP to qualitative data on a dementia caregiving clinical trial provides useful insights for recruitment, retention, and adherence to guidelines for such interventions serving Hispanic and African American dementia caregivers.

Public perceptions and discussions of synthetic nicotine on Twitter.

Background: As alternative replacement products for tobacco-derived nicotine, synthetic nicotine products have recently emerged and gained increasing popularity. This study analyzes public perception and discussion of synthetic nicotine products on Twitter (now "X"). Methods: Through Twitter streaming API (Application Programming Interface), we have collected 2,764 Twitter posts related to synthetic nicotine from December 12, 2021, to October 17, 2022, using keywords related to synthetic nicotine. By applying an inductive approach, two research assistants manually determined the relevance of tweets to synthetic nicotine products and assessed the attitude of tweets as positive, negative, and neutral of tweets toward synthetic nicotine, and the main topics. Results: Among 1,007 tweets related to synthetic nicotine products, the proportion of negative tweets (383/1007, 38.03%) toward synthetic nicotine products was significantly higher than that of positive tweets (218/1007, 21.65%) with a p-value <0.05. Among negative tweets, major topics include the concern about addiction and health risks of synthetic nicotine products (44.91%) and synthetic nicotine as a policy loophole (31.85%). Among positive tweets, top topics include alternative replacement for nicotine (39.91%) and reduced health risks (31.19%). Conclusion: There are mixed attitudes toward synthetic nicotine products on Twitter, resulting from different perspectives. Future research could incorporate demographic information to understand the attitudes of various population groups.

Linking Opinions Shared on Social Media About COVID-19 Public Health Measures to Adherence: Repeated Cross-Sectional Surveys of Twitter Use in Canada.

BACKGROUND: The effectiveness of public health measures (PHMs) depends on population adherence. Social media were suggested as a tool to assess adherence, but representativeness and accuracy issues have been raised. OBJECTIVE: The objectives of this repeated cross-sectional study were to compare self-reported PHM adherence and sociodemographic characteristics between people who used Twitter (subsequently rebranded X) and people who did not use Twitter. METHODS: Repeated Canada-wide web-based surveys were conducted every 14 days from September 2020 to March 2022. Weighted proportions were calculated for descriptive variables. Using Bayesian logistic regression models, we investigated associations between Twitter use, as well as opinions in tweets, and self-reported adherence with mask wearing and vaccination. RESULTS: Data from 40,230 respondents were analyzed. As self-reported, Twitter was used by 20.6% (95% CI 20.1%-21.2%) of Canadians, of whom 29.9% (95% CI 28.6%-31.3%) tweeted about COVID-19. The sociodemographic characteristics differed across categories of Twitter use and opinions. Overall, 11% (95% CI 10.6%-11.3%) of Canadians reported poor adherence to mask-wearing, and 10.8% (95% CI 10.4%-11.2%) to vaccination. Twitter users who tweeted about COVID-19 reported poorer adherence to mask wearing than nonusers, which was modified by the age of the respondents and their geographical region (odds ratio [OR] 0.79, 95% Bayesian credibility interval [BCI] 0.18-1.69 to OR 4.83, 95% BCI 3.13-6.86). The odds of poor adherence to vaccination of Twitter users who tweeted about COVID-19 were greater than those of nonusers (OR 1.76, 95% BCI 1.48-2.07). English- and French-speaking Twitter users who tweeted critically of PHMs were more likely (OR 4.07, 95% BCI 3.38-4.80 and OR 7.31, 95% BCI 4.26-11.03, respectively) to report poor adherence to mask wearing than non-Twitter users, and those who tweeted in support were less likely (OR 0.47, 95% BCI 0.31-0.64 and OR 0.96, 95% BCI 0.18-2.33, respectively) to report poor adherence to mask wearing than non-Twitter users. The OR of poor adherence to vaccination for those tweeting critically about PHMs and for those tweeting in support of PHMs were 4.10 (95% BCI 3.40-4.85) and 0.20 (95% BCI 0.10-0.32), respectively, compared to non-Twitter users. CONCLUSIONS: Opinions shared on Twitter can be useful to public health authorities, as they are associated with adherence to PHMs. However, the sociodemographics of social media users do not represent the general population, calling for caution when using tweets to assess general population-level behaviors.

Large Language Models Can Enable Inductive Thematic Analysis of a Social Media Corpus in a Single Prompt: Human Validation Study.

BACKGROUND: Manually analyzing public health-related content from social media provides valuable insights into the beliefs, attitudes, and behaviors of individuals, shedding light on trends and patterns that can inform public understanding, policy decisions, targeted interventions, and communication strategies. Unfortunately, the time and effort needed from well-trained human subject matter experts makes extensive manual social media listening unfeasible. Generative large language models (LLMs) can potentially summarize and interpret large amounts of text, but it is unclear to what extent LLMs can glean subtle health-related meanings in large sets of social media posts and reasonably report health-related themes. OBJECTIVE: We aimed to assess the feasibility of using LLMs for topic model selection or inductive thematic analysis of large contents of social media posts by attempting to answer the following question: Can LLMs conduct topic model selection and inductive thematic analysis as effectively as humans did in a prior manual study, or at least reasonably, as judged by subject matter experts? METHODS: We asked the same research question and used the same set of social media content for both the LLM selection of relevant topics and the LLM analysis of themes as was conducted manually in a published study about vaccine rhetoric. We used the results from that study as background for this LLM experiment by comparing the results from the prior manual human analyses with the analyses from 3 LLMs: GPT4-32K, Claude-instant-100K, and Claude-2-100K. We also assessed if multiple LLMs had equivalent ability and assessed the consistency of repeated analysis from each LLM. RESULTS: The LLMs generally gave high rankings to the topics chosen previously by humans as most relevant. We reject a null hypothesis (P<.001, overall comparison) and conclude that these LLMs are more likely to include the human-rated top 5 content areas in their top rankings than would occur by chance. Regarding theme identification, LLMs identified several themes similar to those identified by humans, with very low hallucination rates. Variability occurred between LLMs and between test runs of an individual LLM. Despite not consistently matching the human-generated themes, subject matter experts found themes generated by the LLMs were still reasonable and relevant. CONCLUSIONS: LLMs can effectively and efficiently process large social media-based health-related data sets. LLMs can extract themes from such data that human subject matter experts deem reasonable. However, we were unable to show that the LLMs we tested can replicate the depth of analysis from human subject matter experts by consistently extracting the same themes from the same data. There is vast potential, once better validated, for automated LLM-based real-time social listening for common and rare health conditions, informing public health understanding of the public's interests and concerns and determining the public's ideas to address them.

Acceptance of Social Media Recruitment for Clinical Studies Among Patients With Hepatitis B: Mixed Methods Study.

BACKGROUND: Social media platforms are increasingly used to recruit patients for clinical studies. Yet, patients' attitudes regarding social media recruitment are underexplored. OBJECTIVE: This mixed methods study aims to assess predictors of the acceptance of social media recruitment among patients with hepatitis B, a patient population that is considered particularly vulnerable in this context. METHODS: Using a mixed methods approach, the hypotheses for our survey were developed based on a qualitative interview study with 6 patients with hepatitis B and 30 multidisciplinary experts. Thematic analysis was applied to qualitative interview analysis. For the cross-sectional survey, we additionally recruited 195 patients with hepatitis B from 3 clinical centers in Germany. Adult patients capable of judgment with a hepatitis B diagnosis who understood German and visited 1 of the 3 study centers during the data collection period were eligible to participate. Data analysis was conducted using SPSS (version 28; IBM Corp), including descriptive statistics and regression analysis. RESULTS: On the basis of the qualitative interview analysis, we hypothesized that 6 factors were associated with acceptance of social media recruitment: using social media in the context of hepatitis B (hypothesis 1), digital literacy (hypothesis 2), interest in clinical studies (hypothesis 3), trust in nonmedical (hypothesis 4a) and medical (hypothesis 4b) information sources, perceiving the hepatitis B diagnosis as a secret (hypothesis 5a), attitudes toward data privacy in the social media context (hypothesis 5b), and perceived stigma (hypothesis 6). Regression analysis revealed that the higher the social media use for hepatitis B (hypothesis 1), the higher the interest in clinical studies (hypothesis 3), the more trust in nonmedical information sources (hypothesis 4a), and the less secrecy around a hepatitis B diagnosis (hypothesis 5a), the higher the acceptance of social media as a recruitment tool for clinical hepatitis B studies. CONCLUSIONS: This mixed methods study provides the first quantitative insights into social media acceptance for clinical study recruitment among patients with hepatitis B. The study was limited to patients with hepatitis B in Germany but sets out to be a reference point for future studies assessing the attitudes toward and acceptance of social media recruitment for clinical studies. Such empirical inquiries can facilitate the work of researchers designing clinical studies as well as ethics review boards in balancing the risks and benefits of social media recruitment in a context-specific manner.

Why Twitter Sometimes Rewards What Most People Disapprove of: The Case of Cross-Party Political Relations.

Recent evidence has shown that social-media platforms like Twitter (now X) reward politically divisive content, even though most people disapprove of interparty conflict and negativity. We document this discrepancy and provide the first evidence explaining it, using tweets by U.S. Senators and American adults' responses to them. Studies 1a and 1b examined 6,135 such tweets, finding that dismissing tweets received more Likes and Retweets than tweets that engaged constructively with opponents. In contrast, Studies 2a and 2b (N = 856; 1,968 observations) revealed that the broader public, if anything, prefers politicians' engaging tweets. Studies 3 (N = 323; 4,571 observations) and 4 (N = 261; 2,610 observations) supported two distinct explanations for this disconnect. First, users who frequently react to politicians' tweets are an influential yet unrepresentative minority, rewarding dismissing posts because, unlike most people, they prefer them. Second, the silent majority admit that they too would reward dismissing posts more, despite disapproving of them. These findings help explain why popular online content sometimes distorts true public opinion.

The Top Ten Annals of Surgical Oncology Original Articles on Twitter/X: 2020-2023.

Social media has become omnipresent in society, especially given that it enables the rapid and widespread communication of news, events, and information. Social media platforms have become increasingly used by numerous surgical societies to promote meetings and surgical journals to increase the visibility of published content. In September 2020, Annals of Surgical Oncology (ASO) established its Social Media Committee (SMC), which has worked to steadily increase the visibility of published content on social media platforms, namely X (formerly known as Twitter). The purpose of this review is to highlight the 10 ASO original articles with the most engagement on X, based on total number of mentions, since the founding of the SMC. These articles encompass a wide variety of topics from various oncologic disciplines including hepatopancreatobiliary, breast, and gynecologic surgery.

How Does an Online Mental Health Community on Twitter Empower Diverse Population Levels and Groups? A Qualitative Analysis of #BipolarClub.

BACKGROUND: Social media, including online health communities (OHCs), are widely used among both healthy people and those with health conditions. Platforms like Twitter (recently renamed X) have become powerful tools for online mental health communities (OMHCs), enabling users to exchange information, express feelings, and socialize. Recognized as empowering processes, these activities could empower mental health consumers, their families and friends, and society. However, it remains unclear how OMHCs empower diverse population levels and groups. OBJECTIVE: This study aimed to develop an understanding of how empowerment processes are conducted within OMHCs on Twitter by identifying members who shape these communities, detecting the types of empowerment processes aligned with the population levels and groups outlined in Strategy 1 of the Integrated People-Centred Health Services (IPCHS) framework by the World Health Organization (WHO), and clarifying members' involvement tendencies in these processes. METHODS: We conducted our analysis on a Twitter OMHC called #bipolarclub. We captured 2068 original tweets using its hashtag #bipolarclub between December 19, 2022, and January 15, 2023. After screening, 547 eligible tweets by 182 authors were analyzed. Using qualitative content analysis, community members were classified by examining the 182 authors' Twitter profiles, and empowerment processes were identified by analyzing the 547 tweets and categorized according to the WHO's Strategy 1. Members' tendencies of involvement were examined through their contributions to the identified processes. RESULTS: The analysis of #bipolarclub community members unveiled 5 main classifications among the 182 members, with the majority classified as individual members (n=138, 75.8%), followed by health care-related members (n=39, 21.4%). All members declared that they experience mental health conditions, including mental health and general practitioner members, who used the community as consumers and peers rather than for professional services. The analysis of 547 tweets for empowerment processes revealed 3 categories: individual-level processes (6 processes and 2 subprocesses), informal carer processes (1 process for families and 1 process for friends), and society-level processes (1 process and 2 subprocesses). The analysis also demonstrated distinct involvement tendencies among members, influenced by their identities, with individual members engaging in self-expression and family awareness support and health care-related members supporting societal awareness. CONCLUSIONS: The examination of the #bipolarclub community highlights the capability of Twitter-based OMHCs to empower mental health consumers (including those from underserved and marginalized populations), their families and friends, and society, aligning with the WHO's empowerment agenda. This underscores the potential benefits of leveraging Twitter for such objectives. This pioneering study is the very first to analyze how a single OMHC can empower diverse populations, offering various health care stakeholders valuable guidance and aiding them in developing consumer-oriented empowerment programs using such OMHCs. We also propose a structured framework that classifies empowerment processes in OMHCs, inspired by the WHO's Strategy 1 (IPCHS framework).

Impact of a New Gynecologic Oncology Hashtag During Virtual-Only ASCO Annual Meetings: An X (Twitter) Social Network Analysis.

Background: Official conference hashtags are commonly used to promote tweeting and social media engagement. The reach and impact of introducing a new hashtag during an oncology conference have yet to be studied. The American Society of Clinical Oncology (ASCO) conducts an annual global meeting, which was entirely virtual due to the COVID-19 pandemic in 2020 and 2021. Objective: This study aimed to assess the reach and impact (in the form of vertices and edges generated) and X (formerly Twitter) activity of the new hashtags #goASCO20 and #goASCO21 in the ASCO 2020 and 2021 virtual conferences. Methods: New hashtags (#goASCO20 and #goASCO21) were created for the ASCO virtual conferences in 2020 and 2021 to help focus gynecologic oncology discussion at the ASCO meetings. Data were retrieved using these hashtags (#goASCO20 for 2020 and #goASCO21 for 2021). A social network analysis was performed using the NodeXL software application. Results: The hashtags #goASCO20 and #goASCO21 had similar impacts on the social network. Analysis of the reach and impact of the individual hashtags found #goASCO20 to have 150 vertices and 2519 total edges and #goASCO20 to have 174 vertices and 2062 total edges. Mentions and tweets between 2020 and 2021 were also similar. The circles representing different users were spatially arranged in a more balanced way in 2021. Tweets using the #goASCO21 hashtag received significantly more responses than tweets using #goASCO20 (75 times in 2020 vs 360 times in 2021; z value=16.63 and P<.001). This indicates increased engagement in the subsequent year. Conclusions: Introducing a gynecologic oncology specialty-specific hashtag (#goASCO20 and #goASCO21) that is related but different from the official conference hashtag (#ASCO20 and #ASCO21) helped facilitate discussion on topics of interest to gynecologic oncologists during a virtual pan-oncology meeting. This impact was visible in the social network analysis.

Feasibility of big data analytics in disaster psychiatry: Impact of Seoul Itaewon tragedy on sentiment distribution on Twitter.

Numerous studies have highlighted the significant impact of disasters on mental health, often leading to psychiatric disorders among affected individuals. Timely identification of disaster-related mental health problems is crucial to prevent long-term negative consequences and improve individual and community resilience. To address the limitations of prior research that has focused solely on isolated incidents, we analyzed the impact of a recurring Halloween event in Itaewon, South Korea, which culminated tragically in a crowd crush incident in 2022. We conducted sentiment analysis on big data from Korean Twitter to gauge the impact of this disaster on public sentiment. We collected tweets 2 weeks before and after the annual festival from 2020 to 2022, allowing for the consideration of variability across years and days before the disaster. Using a pre-trained RoBERTa neural network model fine-tuned with public sentiment datasets, we categorized tweets into seven pre-defined emotional categories: Anger, sadness, happiness, disgust, fear, surprise, and neutrality. These sentiments were then analyzed as daily time-series data. The overall tweet volume across all sentiment categories increased, particularly showing an increase in the number of tweets indicating "Sadness" in 2022 compared with that in previous years. Post-disaster, a substantial increase was noted in the proportion of tweets expressing "Sadness" and "Fear." This trend was confirmed by Seasonal Autoregressive Integrated Moving Average with Exogenous Regressor models. Notably, there was an increase in the number of tweets expressing all sentiments, including "Happy." However, significant changes in proportions were observed only in tweets categorized as expressing "Sadness" [0.046 (95% CI: 0.024-0.068, P < 0.0001)] and "Fear" [0.033 (95% CI: 0.014-0.051, P < 0.0001)]. Our study demonstrates the feasibility of using sentiment data from social media, combined with sentiment classification, to assess distinct public mental health features following disasters. This approach provides valuable insights into the emotional impact of each event.

Digital Epidemiology of Prescription Drug References on X (Formerly Twitter): Neural Network Topic Modeling and Sentiment Analysis.

BACKGROUND: Data from the social media platform X (formerly Twitter) can provide insights into the types of language that are used when discussing drug use. In past research using latent Dirichlet allocation (LDA), we found that tweets containing "street names" of prescription drugs were difficult to classify due to the similarity to other colloquialisms and lack of clarity over how the terms were used. Conversely, "brand name" references were more amenable to machine-driven categorization. OBJECTIVE: This study sought to use next-generation techniques (beyond LDA) from natural language processing to reprocess X data and automatically cluster groups of tweets into topics to differentiate between street- and brand-name data sets. We also aimed to analyze the differences in emotional valence between the 2 data sets to study the relationship between engagement on social media and sentiment. METHODS: We used the Twitter application programming interface to collect tweets that contained the street and brand name of a prescription drug within the tweet. Using BERTopic in combination with Uniform Manifold Approximation and Projection and k-means, we generated topics for the street-name corpus (n=170,618) and brand-name corpus (n=245,145). Valence Aware Dictionary and Sentiment Reasoner (VADER) scores were used to classify whether tweets within the topics had positive, negative, or neutral sentiments. Two different logistic regression classifiers were used to predict the sentiment label within each corpus. The first model used a tweet's engagement metrics and topic ID to predict the label, while the second model used those features in addition to the top 5000 tweets with the largest term-frequency-inverse document frequency score. RESULTS: Using BERTopic, we identified 40 topics for the street-name data set and 5 topics for the brand-name data set, which we generalized into 8 and 5 topics of discussion, respectively. Four of the general themes of discussion in the brand-name corpus referenced drug use, while 2 themes of discussion in the street-name corpus referenced drug use. From the VADER scores, we found that both corpora were inclined toward positive sentiment. Adding the vectorized tweet text increased the accuracy of our models by around 40% compared with the models that did not incorporate the tweet text in both corpora. CONCLUSIONS: BERTopic was able to classify tweets well. As with LDA, the discussion using brand names was more similar between tweets than the discussion using street names. VADER scores could only be logically applied to the brand-name corpus because of the high prevalence of non-drug-related topics in the street-name data. Brand-name tweets either discussed drugs positively or negatively, with few posts having a neutral emotionality. From our machine learning models, engagement alone was not enough to predict the sentiment label; the added context from the tweets was needed to understand the emotionality of a tweet.