Can accurate demographic information about people who use prescription medications nonmedically be derived from Twitter?

Traditional substance use (SU) surveillance methods, such as surveys, incur substantial lags. Due to the continuously evolving trends in SU, insights obtained via such methods are often outdated. Social media-based sources have been proposed for obtaining timely insights, but methods leveraging such data cannot typically provide fine-grained statistics about subpopulations, unlike traditional approaches. We address this gap by developing methods for automatically characterizing a large Twitter nonmedical prescription medication use (NPMU) cohort (n = 288,562) in terms of age-group, race, and gender. Our natural language processing and machine learning methods for automated cohort characterization achieved 0.88 precision (95% CI:0.84 to 0.92) for age-group, 0.90 (95% CI: 0.85 to 0.95) for race, and 94% accuracy (95% CI: 92 to 97) for gender, when evaluated against manually annotated gold-standard data. We compared automatically derived statistics for NPMU of tranquilizers, stimulants, and opioids from Twitter with statistics reported in the National Survey on Drug Use and Health (NSDUH) and the National Emergency Department Sample (NEDS). Distributions automatically estimated from Twitter were mostly consistent with the NSDUH [Spearman r: race: 0.98 (P < 0.005); age-group: 0.67 (P < 0.005); gender: 0.66 (P = 0.27)] and NEDS, with 34/65 (52.3%) of the Twitter-based estimates lying within 95% CIs of estimates from the traditional sources. Explainable differences (e.g., overrepresentation of younger people) were found for age-group-related statistics. Our study demonstrates that accurate subpopulation-specific estimates about SU, particularly NPMU, may be automatically derived from Twitter to obtain earlier insights about targeted subpopulations compared to traditional surveillance approaches.

Greed communication predicts the approval and reach of US senators' tweets.

Social media are at the forefront of modern political campaigning. They allow politicians to communicate directly with constituents and constituents to endorse politicians' messages and share them with their networks. Analyzing every tweet of all US senators holding office from 2013 to 2021 (861,104 tweets from 140 senators), we identify a psycholinguistic factor, greed communication, that robustly predicts increased approval (favorites) and reach (retweets). These effects persist when tested against diverse established psycholinguistic predictors of political content dissemination on social media and various other psycholinguistic variables. We further find that greed communication in the tweets of Democratic senators is associated with greater approval and retweeting compared to greed communication in the tweets of Republican senators, especially when those tweets also mention political outgroups.

Online engagement with 2020 election misinformation and turnout in the 2021 Georgia runoff election.

Following the 2020 general election, Republican elected officials, including then-President Donald Trump, promoted conspiracy theories claiming that Joe Biden's close victory in Georgia was fraudulent. Such conspiratorial claims could implicate participation in the Georgia Senate runoff election in different ways-signaling that voting doesn't matter, distracting from ongoing campaigns, stoking political anger at out-partisans, or providing rationalizations for (lack of) enthusiasm for voting during a transfer of power. Here, we evaluate the possibility of any on-average relationship with turnout by combining behavioral measures of engagement with election conspiracies online and administrative data on voter turnout for 40,000 Twitter users registered to vote in Georgia. We find small, limited associations. Liking or sharing messages opposed to conspiracy theories was associated with higher turnout than expected in the runoff election, and those who liked or shared tweets promoting fraud-related conspiracy theories were slightly less likely to vote.

Strategic identity signaling in heterogeneous networks.

SignificanceMuch of online conversation today consists of signaling one's political identity. Although many signals are obvious to everyone, others are covert, recognizable to one's ingroup while obscured from the outgroup. This type of covert identity signaling is critical for collaborations in a diverse society, but measuring covert signals has been difficult, slowing down theoretical development. We develop a method to detect covert and overt signals in tweets posted before the 2020 US presidential election and use a behavioral experiment to test predictions of a mathematical theory of covert signaling. Our results show that covert political signaling is more common when the perceived audience is politically diverse and open doors to a better understanding of communication in politically polarized societies.

An analysis of emotions and the prominence of positivity in #BlackLivesMatter tweets.

Emotions are a central driving force of activism; they motivate participation in movements and encourage sustained involvement. We use natural language processing techniques to analyze emotions expressed or solicited in tweets about 2020 Black Lives Matter protests. Traditional off-the-shelf emotion analysis tools often fail to generalize to new datasets and are unable to adapt to how social movements can raise new ideas and perspectives in short time spans. Instead, we use a few-shot domain adaptation approach for measuring emotions perceived in this specific domain: tweets about protests in May 2020 following the death of George Floyd. While our analysis identifies high levels of expressed anger and disgust across overall posts, it additionally reveals the prominence of positive emotions (encompassing, e.g., pride, hope, and optimism), which are more prevalent in tweets with explicit pro-BlackLivesMatter hashtags and correlated with on the ground protests. The prevalence of positivity contradicts stereotypical portrayals of protesters as primarily perpetuating anger and outrage. Our work offers data, analyses, and methods to support investigations of online activism and the role of emotions in social movements.

COVID-19, climate change, and the finite pool of worry in 2019 to 2021 Twitter discussions.

Climate change mitigation has been one of the world's most salient issues for the past three decades. However, global policy attention has been partially diverted to address the COVID-19 pandemic for the past 2 y. Here, we explore the impact of the pandemic on the frequency and content of climate change discussions on Twitter for the period of 2019 to 2021. Consistent with the "finite pool of worry" hypothesis both at the annual level and on a daily basis, a larger number of COVID-19 cases and deaths is associated with a smaller number of "climate change" tweets. Climate change discussion on Twitter decreased, despite 1) a larger Twitter daily active usage in 2020 and 2021, 2) greater coverage of climate change in the traditional media in 2021, 3) a larger number of North Atlantic Ocean hurricanes, and 4) a larger wildland fires area in the United States in 2020 and 2021. Further evidence supporting the finite pool of worry is the significant relationship between daily COVID-19 cases/deaths on the one hand and the public sentiment and emotional content of climate change tweets on the other. In particular, increasing COVID-19 numbers decrease negative sentiment in climate change tweets and the emotions related to worry and anxiety, such as fear and anger.

English tweets on allergy: Content analysis and association with surveillance data.

BACKGROUND: Analysis of X (formerly Twitter) posts can inform on the interest/perceptions that social media users have on health subjects. In this study, we aimed to analyse tweets on allergic conditions, comparing them with surveillance data. METHODS: We retrieved tweets from England on "allergy," "asthma," and "allergic rhinitis," published between 2016 and 2021. We estimated the correlation between the frequency of tweets on "asthma" and "allergic rhinitis" and English surveillance data on the incidence of asthma and allergic rhinitis medical visits. We performed sentiment analysis, computing a score informing on the emotional tone of assessed tweets. We applied a topic modelling approach to identify topics (clusters of words frequently occurring together) for tweets on each assessed condition. RESULTS: We analysed a total of 13,605 tweets on "allergy," 7767 tweets on "asthma," and 11,974 tweets on "allergic rhinitis." Food-related words were preponderant on tweets on "allergy," while "eyes" was the most frequent meaningful word on "allergy rhinitis" tweets. We observed seasonal patterns for tweets on "allergic rhinitis," both in their frequency and sentiment - the incidence of allergic rhinitis medical visits was moderately to strongly correlated with the frequency (ρ = 0.866) and sentiment (ρ = -0.474) of tweets on "allergic rhinitis." For tweets on "asthma," no such patterns/correlations were observed. The average sentiment score was negative for all assessed conditions, ranging from -0.004 ("asthma") to -0.083 ("allergic rhinitis"). CONCLUSIONS: Tweets on "allergic rhinitis" displayed a seasonal pattern regarding their frequency and sentiment, which correlated with surveillance data. No such patterns were observed for "asthma."

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.

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.

Associations between news coverage, social media discussions, and search trends about celebrity deaths, screening, and other colorectal cancer-related events.

OBJECTIVE: Colorectal cancer (CRC) is the third leading cause of cancer death among both men and women in the United States. CRC-related events may increase media coverage and public attention, boosting awareness and prevention. This study examined associations between several types of CRC events (including unplanned celebrity cancer deaths and planned events like national CRC awareness months, celebrity screening behavior, and screening guideline changes) and news coverage, Twitter discussions, and Google search trends about CRC and CRC screening. METHODS: We analyzed data from U.S. national news media outlets, posts scraped from Twitter, and Google Trends on CRC and CRC screening during a three-year period from 2020 to 2022. We used burst detection methods to identify temporal spikes in the volume of news, tweets, and search after each CRC-related event. RESULTS: There is a high level of heterogeneity in the impact of celebrity CRC events. Celebrity CRC deaths were more likely to precede spikes in news and tweets about CRC overall than CRC screening. Celebrity screening preceded spikes in news and tweets about screening but not searches. Awareness months and screening guideline changes did precede spikes in news, tweets, and searches about screening, but these spikes were inconsistent, not simultaneous, and not as large as those events concerning most prominent public figures. CONCLUSIONS: CRC events provide opportunities to increase attention to CRC. Media and public health professionals should actively intervene during CRC events to increase emphasis on CRC screening and evidence-based recommendations.

Tweeting environmental pollution: Analyzing twitter language to uncover its correlation with county-level obesity rates in the United States.

BACKGROUND: Environmental pollution has been linked to obesogenic tendencies. Using environmental-related posts from Twitter (now known as X) from U.S. counties, we aim to uncover the association between Twitter linguistic data and U.S. county-level obesity rates. METHODS: Analyzing nearly 300 thousand tweets from January 2020 to December 2020 across 207 U.S. counties, using an innovative Differential Language Analysis technique and drawing county-level obesity data from the 2020 Food Environment Atlas to identify distinct linguistic features in Twitter relating to environmental-related posts correlated with socioeconomic status (SES) index indicators, obesity rates, and obesity rates controlled for SES index indicators. We also employed predictive modeling to estimate Twitter language's predictive capacity for obesity rates. RESULTS: Results revealed a negative correlation between environmental-related tweets and obesity rates, both before and after adjusting for SES. Contrarily, non-environmental-related tweets showed a positive association with higher county-level obesity rates, indicating that individuals living in counties with lower obesity rates tend to tweet environmental-related language more frequently than those living in counties with higher obesity rates. The findings suggest that linguistic patterns and expressions employed in discussing environmental-related themes on Twitter can offer unique insights into the prevailing cross-sectional patterns of obesity rates. CONCLUSIONS: Although Twitter users are a subset of the general population, incorporating environmental-related tweets and county-level obesity rates and using a novel language analysis technique make this study unique. Our results indicated that Twitter users engaging in more active dialog about environmental concerns might exhibit healthier lifestyle practices, contributing to reduced obesity rates.

A Study on Perceptions of Undetectable = Untransmittable Among Gay Men with Human Immunodeficiency Virus in the HIV Community on Twitter in Japan: An Exploratory Qualitative Study Using a Modified Grounded Theory Approach.

This study explores the perceptions of the Undetectable = Untransmittable (U = U) campaign among gay men with HIV in Japan who are part of the HIV community on Twitter. We conducted detailed semistructured interviews with 12 participants using a modified grounded theory approach. The analysis resulted in 31 concepts, 5 subcategories, 9 categories, and 2 core categories. The relationship between categories and core categories was examined in conjunction with the transcriptions, yielding a comprehensive category map depicting the process of understanding U = U. The three main processes emerged: participants expressed "expectations for improvement," underwent stages of "understanding U = U," and encountered "dilemmas" in forming their opinions. There are two routes to "understanding U = U": Route 1 involved a frictionless understanding of U = U, and Route 2 involved difficulty in understanding the slogan. In both routes, participants experienced the dilemma of "but I still have HIV" and regarding its ease of use. These dilemmas and difficulties in understanding U = U affected their "expectations for improvement." Efforts to promote U = U in Japan must address challenges in public understanding and related dilemmas. This entails reformulating the U = U message in simpler terms, leveraging professional explanations, disseminating it to a broader audience, and incorporating ideas from individuals living with HIV to enhance the message.

Utilizing sentiment analysis of X data to document the evolution of colorectal surgical innovations: The case of transanal total mesorectal excision.

AIM: The evolution of the utility of medical social media and its global reach has led to a much greater speed of dissemination of medical innovation, such as transanal total mesorectal excision (TaTME). The acceptability and discussions surrounding such innovations can be followed online. Here, we sought to determine if online discussions over time could match known models of innovation evolution using the example of TaTME since its initial description in 2010. METHODS: Data on using the X hashtag #TaTME were analysed using the social media analytics tool Brandwatch. Trends in mentions, impressions and reach were highlighted over 13 years (1 May 2010 to 31 July 2023). Each mention's sentiment and emotional connotations were analysed using Brandwatch's natural language processing approach. RESULTS: We identified 18 525 mentions of #TaTME by healthcare professionals, reaching over 30.6 million X users. A Gartner's hype-cycle-like pattern was identified for mention volume and emotional connotation over time. The majority of mentions had a neutral (84%; n = 15 341) or positive connotation (15%, n = 2675). A peak of negatively connotated mentions was identified surrounding the temporary suspension of TaTME in 2019. CONCLUSION: This study presents a novel method of monitoring online discussions surrounding new surgical innovations by healthcare professionals based on sentiment analysis of public social media data. Mention volume and emotional connotation were the most accurate parameters closely resembling Gartner's hype cycle.

Embracing the (r)evolution of social media and digital scholarship in pediatric nephrology education.

Free Open-Access Medical Education (FOAMed) has transformed medical education in the past decade by complementing and substituting for traditional medical education when needed. The attractiveness of FOAMed resources is due to their inexpensive nature, wide availability, and user ability to access on demand across a variety of devices, making it easy to create, share, and participate. The subject of nephrology is complex, fascinating, and challenging. Traditional didactic lectures can be passive and ineffective in uncovering these difficult concepts and may need frequent revisions. Active teaching methods like flipped classrooms have shown some benefits, and these benefits can only be multifold with current social media tools. Social media will inspire the involvement of students and allow them to create and share educational content in a "trendy way," encouraging the participation of their peers and thus building an educational environment more conducive to them while promoting revision and retainment. FOAMed also promotes asynchronous learning, spaced learning, microlearning, and multimodal presentation with a meaningful variation. This article discusses the evolution of digital education, social media platforms, tools for creating and developing FOAMed resources, and digital scholarship.

Assessment of beliefs and attitudes towards benzodiazepines using machine learning based on social media posts: an observational study.

BACKGROUND: Benzodiazepines are frequently prescribed drugs; however, their prolonged use can lead to tolerance, dependence, and other adverse effects. Despite these risks, long-term use remains common, presenting a public health concern. This study aims to explore the beliefs and opinions held by the public regarding benzodiazepines, as understanding these perspectives may provide insights into their usage patterns. METHODS: We collected public tweets published in English between January 1, 2019, and October 31, 2020, that mentioned benzodiazepines. The content of each tweet and the characteristics of the users were analyzed using a mixed-method approach, including manual analysis and semi-supervised machine learning. RESULTS: Over half of the Twitter users highlighted the efficacy of benzodiazepines, with minimal discussion of their side effects. The most active participants in these conversations were patients and their families, with health professionals and institutions being notably absent. Additionally, the drugs most frequently mentioned corresponded with those most commonly prescribed by healthcare professionals. CONCLUSIONS: Social media platforms offer valuable insights into users' experiences and opinions regarding medications. Notably, the sentiment towards benzodiazepines is predominantly positive, with users viewing them as effective while rarely mentioning side effects. This analysis underscores the need to educate physicians, patients, and their families about the potential risks associated with benzodiazepine use and to promote clinical guidelines that support the proper management of these medications. CLINICAL TRIAL NUMBER: Not applicable.

"Anxiety is not cute" analysis of twitter users' discourses on romanticizing mental illness.

BACKGROUND: The proliferation of social media platforms has provided a unique space for discourse on mental health, originally intended to destigmatize mental illness. However, recent discourses on these platforms have shown a concerning shift towards the romanticization of mental health issues. This research focuses on Twitter (now called X) users' authentic discussions on the phenomenon of romanticizing mental health, aiming to uncover unique perspectives, themes, and language used by users when engaging with this complex topic. METHODS: A comprehensive content analysis was conducted on 600 relevant tweets, with the application of topic modeling techniques. This methodology allowed for the identification and exploration of six primary themes that emerged from Twitter users' discussions. Statistical tests were not applied in this qualitative analysis. RESULTS: The study identified six primary themes resulting from Twitter users' discussions on the romanticization of mental health. These themes include rejecting/critiquing the glamorization of mental health, monetization of mental health by corporate organizations, societal misconceptions of mental health, the role of traditional media and social media, unfiltered realities of depression, and the emphasis on not romanticizing mental health. CONCLUSIONS: This study provides valuable insights into the multifaceted discourses surrounding the romanticization of mental health on Twitter. It highlights users' critiques, concerns, and calls for change, emphasizing the potential harm caused by romanticizing mental illness. The findings underscore the importance of fostering responsible and empathetic discussions about mental health on social media platforms. By examining how Twitter users interact with and respond to the romanticization of mental health, this research advances our understanding of emerging perspectives on mental health issues among social media users, particularly young adolescents. The study also underscores the effects of this phenomenon on individuals, society, and the mental health community. Overall, this research emphasizes the need for more responsible and knowledgeable discussions around mental health in the digital age.

Refueling a Quiet Fire: Old Truthers and New Discontent in the Wake of COVID-19.

This article investigates the factors that contributed to the proliferation of online COVID skepticism on Twitter across Italian municipalities in 2020. We demonstrate that sociodemographic factors were likely to mitigate the emergence of skepticism, whereas populist political leanings were more likely to foster it. Furthermore, pre-COVID anti-vaccine sentiment, represented by "old truthers" on Twitter, amplified online COVID skepticism in local communities. Additionally, exploiting the spatial variation in restrictive economic policies with severe implications for suspended workers in nonessential economic sectors, we find that COVID skepticism spreads more in municipalities significantly affected by the economic lockdown. Finally, the diffusion of COVID skepticism is positively associated with COVID vaccine hesitancy.

Developing large language models to detect adverse drug events in posts on x.

Adverse drug events (ADEs) are one of the major causes of hospital admissions and are associated with increased morbidity and mortality. Post-marketing ADE identification is one of the most important phases of drug safety surveillance. Traditionally, data sources for post-marketing surveillance mainly come from spontaneous reporting system such as the Food and Drug Administration Adverse Event Reporting System (FAERS). Social media data such as posts on X (formerly Twitter) contain rich patient and medication information and could potentially accelerate drug surveillance research. However, ADE information in social media data is usually locked in the text, making it difficult to be employed by traditional statistical approaches. In recent years, large language models (LLMs) have shown promise in many natural language processing tasks. In this study, we developed several LLMs to perform ADE classification on X data. We fine-tuned various LLMs including BERT-base, Bio_ClinicalBERT, RoBERTa, and RoBERTa-large. We also experimented ChatGPT few-shot prompting and ChatGPT fine-tuned on the whole training data. We then evaluated the model performance based on sensitivity, specificity, negative predictive value, positive predictive value, accuracy, F1-measure, and area under the ROC curve. Our results showed that RoBERTa-large achieved the best F1-measure (0.8) among all models followed by ChatGPT fine-tuned model with F1-measure of 0.75. Our feature importance analysis based on 1200 random samples and RoBERTa-Large showed the most important features are as follows: "withdrawals"/"withdrawal", "dry", "dealing", "mouth", and "paralysis". The good model performance and clinically relevant features show the potential of LLMs in augmenting ADE detection for post-marketing drug safety surveillance.

Mapping loneliness through comparative analysis of USA and India using social intelligence analysis.

Loneliness, a widespread global public health concern, has far-reaching implications for mental and physical well-being, as well as economic productivity. It also increases the risk of life-threatening conditions. This study conducts a comparative analysis of loneliness in the USA and India using Twitter data, aiming to contribute to a global public health map on loneliness. Collecting 4.1 million tweets globally in October 2022 containing keywords like "lonely", "loneliness", and "alone", the analysis focuses on sentiment and psychosocial linguistic features. Utilizing the Valence Aware Dictionary for Sentiment Reasoning (VADER) for sentiment analysis, the study explores variations in loneliness dynamics across cities, revealing geographical distinctions in correlated topics. The tweets with negative sentiment were further analyzed for psychosocial linguistic features to find a meaningful correlation between loneliness and socioeconomic and emotional themes and factors. Results give detailed top correlated topics with loneliness for each city. The results showed that the dynamics of loneliness through the topics correlated vary across geographical locations. Social media data can be used to capture the dynamics of loneliness which can vary from one place to another depending on the socioeconomic and cultural norms and sociopolitical policies. Social media data to understand loneliness can also provide useful information and insight for public health and policymaking.

Exploring food poverty experiences in the German Twitter-Sphere.

BACKGROUND: This study investigates the subjective perceptions of food poverty in Germany by analysing Twitter discourse using the German-language hashtag #IchBinArmutsbetroffen (#IamPovertyAffected) and examines the extent to which various dimensions of a multidimensional theoretical model of food poverty are represented in the discourse. METHODS: Employing a combination of computational social science and qualitative social research methods, the research identifies, and analyses tweets related to nutrition by applying a hierarchical dictionary search and qualitative content analysis. By examining the narratives and statements of individuals affected by food poverty, the study also investigates the interplay among different subdimensions of this phenomenon. RESULTS: The analysis of 1,112 tweets revealed that 57.96% focused on the material dimension and 42.04% on the social dimension of food poverty, suggesting a relatively balanced emphasis on material and social aspects of food poverty in the narratives of those affected. The findings reveal that tweets on material food poverty underscore economic challenges and resource scarcity for food. Social food poverty tweets demonstrate widespread deprivation in social participation, leading to isolation, exclusion, and social network loss. Overall, the results elucidate intricate interconnections among subdimensions and multidimensional manifestations of food poverty. CONCLUSIONS: This study contributes methodologically by presenting an approach for extracting food-related textual social media data and empirically by providing novel insights into the perceptions and multifaceted manifestations of food poverty in Germany. The results can aid in a better understanding of the phenomenon of food poverty as it currently manifests in Germany, and in developing targeted social, health-promoting, and political measures that address more effectively the empirically evident multidimensionality of the phenomenon.