Social media language of healthcare super-utilizers.
Ontology highlight
ABSTRACT:
SUBMITTER: Guntuku SC
PROVIDER: S-EPMC7994843 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveWe explore the personality of counties as assessed through linguistic patterns on social media. Such studies were previously limited by the cost and feasibility of large-scale surveys; however, language-based computational models applied to large social media datasets now allow for large-scale personality assessment.MethodWe applied a language-based assessment of the five factor model of personality to 6,064,267 U.S. Twitter users. We aggregated the Twitter-based personality scores to 2,041 counties and compared to political, economic, social, and health outcomes measured through surveys and by government agencies.ResultsThere was significant personality variation across counties. Openness to experience was higher on the coasts, conscientiousness was uniformly spread, extraversion was higher in southern states, agreeableness was higher in western states, and emotional stability was highest in the south. Across 13 outcomes, language-based personality estimates replicated patterns that have been observed in individual-level and geographic studies. This includes higher Republican vote share in less agreeable counties and increased life satisfaction in more conscientious counties.ConclusionsResults suggest that regions vary in their personality and that these differences can be studied through computational linguistic analysis of social media. Furthermore, these methods may be used to explore other psychological constructs across geographies.
| S-EPMC9714561 | biostudies-literature
Project description:Hate speech on social media threatens the mental health of its victims and poses severe safety risks to modern societies. Yet, the mechanisms underlying its proliferation, though critical, have remained largely unresolved. In this work, we hypothesize that moralized language predicts the proliferation of hate speech on social media. To test this hypothesis, we collected three datasets consisting of N = 691,234 social media posts and ∼35.5 million corresponding replies from Twitter that have been authored by societal leaders across three domains (politics, news media, and activism). Subsequently, we used textual analysis and machine learning to analyze whether moralized language carried in source tweets is linked to differences in the prevalence of hate speech in the corresponding replies. Across all three datasets, we consistently observed that higher frequencies of moral and moral-emotional words predict a higher likelihood of receiving hate speech. On average, each additional moral word was associated with between 10.76% and 16.48% higher odds of receiving hate speech. Likewise, each additional moral-emotional word increased the odds of receiving hate speech by between 9.35 and 20.63%. Furthermore, moralized language was a robust out-of-sample predictor of hate speech. These results shed new light on the antecedents of hate speech and may help to inform measures to curb its spread on social media.
| S-EPMC9837664 | biostudies-literature
Project description:Health promoters have been unable to reach and engage people on social media (SM) to the extent that food industry brands and lifestyle personalities have. The objective of this study was to identify the SM post strategies associated with higher engagement in nutrition and food-related posts using a retrospective content analysis. The six most engaging posts from both Facebook and Instagram's 10 most successful nutrition and food-related accounts were analysed across four fields. Subjective and objective post strategies were coded on 736 posts, and associations with engagement were explored using the Least Absolute Shrinkage and Selection Operator (LASSO). Lifestyle personalities recorded the highest absolute engagement, while health promoters recorded the highest engagement relative to follower count. Strategies associated with higher Facebook engagement included using hashtags and prompting engagement through announcements, while on Instagram, higher engagement was associated with higher caption counts, providing health information links, prompting engagement through strategies that require an action, and using humorous strategies. Strategies associated with lower Instagram engagement included reposted content, general encouragement to eat strategies, encouragement to exercise strategies, not inducing any emotion/hedonic sensations, and providing a negative tone. Health promoters should adapt SM posts to the different SM platforms and utilise strategies associated with higher engagement to engage with their audience on SM.
| S-EPMC7551727 | biostudies-literature
Project description:The real-time availability of the Internet has engaged millions of users around the world. The usage of regional languages is being preferred for effective and ease of communication that is causing multilingual data on social networks and news channels. People share ideas, opinions, and events that are happening globally i.e., sports, inflation, protest, explosion, and sexual assault, etc. in regional (local) languages on social media. Extraction and classification of events from multilingual data have become bottlenecks because of resource lacking. In this research paper, we presented the event classification task for the Urdu language text existing on social media and the news channels by using machine learning classifiers. The dataset contains more than 0.1 million (102,962) labeled instances of twelve (12) different types of events. The title, its length, and the last four words of a sentence are used as features to classify the events. The Term Frequency-Inverse Document Frequency (tf-idf) showed the best results as a feature vector to evaluate the performance of the six popular machine learning classifiers. Random Forest (RF) and K-Nearest Neighbor (KNN) are among the classifiers that out-performed among other classifiers by achieving 98.00% and 99.00% accuracy, respectively. The novelty lies in the fact that the features aforementioned are not applied, up to the best of our knowledge, in the event extraction of the text written in the Urdu language.
| S-EPMC8627225 | biostudies-literature
Project description:BackgroundSuper-utilizers with 4 or more admissions per year frequently receive low-quality care and disproportionately contribute to healthcare costs. Inpatient care fragmentation (admission to multiple different hospitals) in this population has not been well described.ObjectiveTo determine the prevalence of super-utilizers who receive fragmented care across different hospitals and to describe associated risks, costs, and health outcomes.Research designWe analyzed inpatient data from the Health Care Utilization Project's State Inpatient and Emergency Department database from 6 states from 2013. After identifying hospital super-utilizers, we stratified by the number of different hospitals visited in a 1-year period. We determined how patient demographics, costs, and outcomes varied by degree of fragmentation. We then examined how fragmentation would influence a hospital's ability to identify super-utilizers.SubjectsAdult patients with 4 or more inpatient stays in 1 year.MeasuresPatient demographics, cost, 1-year hospital reported mortality, and probability that a single hospital could correctly identify a patient as a super-utilizer.ResultsOf the 167,515 hospital super-utilizers, 97,404 (58.1%) visited more than 1 hospital in a 1-year period. Fragmentation was more likely among younger, non-white, low-income, under-insured patients, in population-dense areas. Patients with fragmentation were more likely to be admitted for chronic disease management, psychiatric illness, and substance abuse. Inpatient fragmentation was associated with higher yearly costs and lower likelihood of being identified as a super-utilizer.ConclusionsInpatient care fragmentation is common among super-utilizers, disproportionately affects vulnerable populations. It is associated with high yearly costs and a decreased probability of correctly identifying super-utilizers.
| S-EPMC8045386 | biostudies-literature
Project description: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.
| S-EPMC10998627 | biostudies-literature
Project description:Targeting of location-specific aid for the U.S. opioid epidemic is difficult due to our inability to accurately predict changes in opioid mortality across heterogeneous communities. AI-based language analyses, having recently shown promise in cross-sectional (between-community) well-being assessments, may offer a way to more accurately longitudinally predict community-level overdose mortality. Here, we develop and evaluate, TROP (Transformer for Opiod Prediction), a model for community-specific trend projection that uses community-specific social media language along with past opioid-related mortality data to predict future changes in opioid-related deaths. TOP builds on recent advances in sequence modeling, namely transformer networks, to use changes in yearly language on Twitter and past mortality to project the following year's mortality rates by county. Trained over five years and evaluated over the next two years TROP demonstrated state-of-the-art accuracy in predicting future county-specific opioid trends. A model built using linear auto-regression and traditional socioeconomic data gave 7% error (MAPE) or within 2.93 deaths per 100,000 people on average; our proposed architecture was able to forecast yearly death rates with less than half that error: 3% MAPE and within 1.15 per 100,000 people.
| S-EPMC9992514 | biostudies-literature
Project description:This paper presents dataset collected from social networks that are mostly used by youth of Commonwealth of Independent States (CIS) countries. The data was collected from public accounts of VKontakte social network by using VK.api and applying the most used keywords that would signify depressive mood. The collected data was classified by psychologists into two types: depressive and non-depressive. The dataset consists of 32 018 depressive posts and 32 021 non-depressive posts. Since the most common language that is spoken in CIS countries is Russian, the posts are written in Russian, consequently the collected data is in Russian language as well. The data can mostly be useful for researchers who explore tendencies to depression in CIS countries. The dataset is important for the research community, as it was not only collected from open sources, but also marked by our psychiatrists from the republican scientific and practical center of mental health. Since the dataset has very high validity, it can be used for further research in the field of mental health.
| S-EPMC7016367 | biostudies-literature
Project description:Social media was a heavily used platform by people in different countries to express their opinions about different crises, especially during the Covid-19 pandemics. This dataset is created through collecting people's comments in the news items on the official Facebook site of the National Institute of Public Health of Kosovo. The dataset contains a total of 10,132 comments that are human-annotated in the Albanian language as a low-resource language. The dataset was collected from March 12, 2020, and this coincides with the emergence of the first confirmed Covid-19 case in Kosovo until August 31, 2020, when the second wave started. Due to the scarcity of labeled data for low-resource languages, the dataset can be used by the research community in the field of machine learning, information retrieval, affective computing, as well as by the public agencies and decision makers.
| S-EPMC9272335 | biostudies-literature
Project description:Social media is increasingly utilized as a resource in healthcare. We sought to identify perceptions of using social media as an educational tool among healthcare practitioners. An electronic survey was distributed to healthcare administrators, nurses, nurse practitioners, pharmacists, physicians, and physician assistants f hospital systems and affiliated health science schools in Georgia, Maryland, South Carolina, and Wisconsin. Survey questions evaluated respondents' use and views of social media for educational purposes and workplace accessibility using a Likert scale (1 = strongly disagree, 5 = strongly agree). Nurses (75%), pharmacists (11%), and administrators (7%) were the most frequent respondents. Facebook® (27%), Pinterest® (17%), and Instagram® (17%) were the most frequently accessed social media platforms. Nearly 85% agreed or strongly agreed that social media can be an effective tool for educational purposes. Among those who had social media platforms, 43.0% use them for educational purposes. Pinterest® (30%), Facebook® (22%), LinkedIn® (16%), and Twitter® (14%) were most frequently used for education. About 50% of respondents had limited or no access to social media at work. Administrators, those with unlimited and limited work access, and respondents aged 20-29 and 30-39 years were more likely to agree that social media is an educational tool (OR: 3.41 (95% CI 1.31 to 8.84), 4.18 (95% CI 2.30 to 7.60), 1.66 (95% CI 1.22 to 2.25), 4.40 (95% CI 2.80 to 6.92), 2.14 (95% CI 1.53 to 3.01) respectively). Residents, physicians, and those with unlimited access were less likely to agree with allowing social media access at work for educational purposes only. Healthcare practitioners frequently utilize social media, and many believe it can be an effective educational tool in healthcare.
| S-EPMC7004337 | biostudies-literature