Dataset Information

Identifying the effects of social media on health behavior: Data from a large-scale online experiment.

ABSTRACT: Sedentary lifestyle is an escalating epidemic. Little is known about whether or how social media can be used to design a cost-effective solution for sedentary lifestyle. In this article we describe the data from a randomized controlled trial (RCT) that evaluated two prominent strategies for conducting exercise interventions using elements of social media: motivational media campaigns and online peer networks. The data file includes 217 participants' basic demographic information, number of exercise class enrollments over 13 weeks, and self-reported number of days for exercise activities in the previous 7 days at baseline. Among the 217, 164 also have data on self-reported number of days for exercise activities at the post-program. Data are supplied with this article. The interpretation of these data can be found in the research article published by the authors in Preventive Medicine Reports in 2015 [1].

SUBMITTER: Zhang J

PROVIDER: S-EPMC4610960 | biostudies-literature | 2015 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Identifying the effects of social media on health behavior: Data from a large-scale online experiment.

Zhang Jingwen J Brackbill Devon D Yang Sijia S Centola Damon D

Data in brief 20151013

Sedentary lifestyle is an escalating epidemic. Little is known about whether or how social media can be used to design a cost-effective solution for sedentary lifestyle. In this article we describe the data from a randomized controlled trial (RCT) that evaluated two prominent strategies for conducting exercise interventions using elements of social media: motivational media campaigns and online peer networks. The data file includes 217 participants' basic demographic information, number of exerc ...[more]

PMID: 26594655

Similar Datasets

Project description:BackgroundAntidepressants are known to show heterogeneous effects across individuals and conditions, posing challenges to understanding their efficacy in mental health treatment. Social media platforms enable individuals to share their day-to-day concerns with others and thereby can function as unobtrusive, large-scale, and naturalistic data sources to study the longitudinal behavior of individuals taking antidepressants.ObjectiveWe aim to understand the side effects of antidepressants from naturalistic expressions of individuals on social media.MethodsOn a large-scale Twitter data set of individuals who self-reported using antidepressants, a quasi-experimental study using unsupervised language analysis was conducted to extract keywords that distinguish individuals who improved and who did not improve following the use of antidepressants. The net data set consists of over 8 million Twitter posts made by over 300,000 users in a 4-year period between January 1, 2014, and February 15, 2018.ResultsFive major side effects of antidepressants were studied: sleep, weight, eating, pain, and sexual issues. Social media language revealed keywords related to these side effects. In particular, antidepressants were found to show a spectrum of effects from decrease to increase in each of these side effects.ConclusionsThis work enhances the understanding of the side effects of antidepressants by identifying distinct linguistic markers in the longitudinal social media data of individuals showing the most and least improvement following the self-reported intake of antidepressants. One implication of this work concerns the potential of social media data as an effective means to support digital pharmacovigilance and digital therapeutics. These results can inform clinicians in tailoring their discussion and assessment of side effects and inform patients about what to potentially expect and what may or may not be within the realm of normal aftereffects of antidepressants.

Project description:BackgroundDigital learning environments have become very common in the training of medical professionals, and students often use such platforms for exam preparation. Multiple choice questions (MCQs) are a common format in medical exams and are used by students to prepare for said exams.ObjectiveWe aimed to examine whether particular learning activities contributed more strongly than others to users' exam performance.MethodsWe analyzed data from users of an online platform that provides learning materials for medical students in preparation for their final exams. We analyzed whether the number of learning cards viewed and the number of MCQs taken were positively related to learning outcomes. We also examined whether viewing learning cards or answering MCQs was more effective. Finally, we tested whether taking individual notes predicted learning outcomes, and whether taking notes had an effect after controlling for the effects of learning cards and MCQs. Our analyses from the online platform Amboss are based on user activity data, which supplied the number of learning cards studied and test questions answered. We also included the number of notes from each of those 23,633 users who had studied at least 200 learning cards and had answered at least 1000 test exam questions in the 180 days before their state exam. The activity data for this analysis was collected retrospectively, using Amboss archival usage data from April 2014 to April 2017. Learning outcomes were measured using the final state exam scores that were calculated by using the answers voluntarily entered by the participants.ResultsWe found correlations between the number of cards studied (r=.22; P<.001) and the number of test questions that had been answered (r=.23; P<.001) with the percentage of correct answers in the learners' medical exams. The number of test questions answered still yielded a significant effect, even after controlling for the number of learning cards studied using a hierarchical regression analysis (β=.14; P<.001; ΔR2=.017; P<.001). We found a negative interaction between the number of learning cards and MCQs, indicating that users with high scores for learning cards and MCQs had the highest exam scores. Those 8040 participants who had taken at least one note had a higher percentage of correct answers (80.94%; SD=7.44) than those who had not taken any notes (78.73%; SD=7.80; t23631=20.95; P<.001). In a stepwise regression, the number of notes the participants had taken predicted the percentage of correct answers over and above the effect of the number of learning cards studied and of the number of test questions entered in step one (β=.06; P<.001; ΔR2=.004; P<.001).ConclusionsThese results show that online learning platforms are particularly helpful whenever learners engage in active elaboration in learning material, such as by answering MCQs or taking notes.

Project description:BackgroundFor an emergent pandemic, such as COVID-19, the statistics of symptoms based on hospital data may be biased or delayed due to the high proportion of asymptomatic or mild-symptom infections that are not recorded in hospitals. Meanwhile, the difficulty in accessing large-scale clinical data also limits many researchers from conducting timely research.ObjectiveGiven the wide coverage and promptness of social media, this study aimed to present an efficient workflow to track and visualize the dynamic characteristics and co-occurrence of symptoms for the COVID-19 pandemic from large-scale and long-term social media data.MethodsThis retrospective study included 471,553,966 COVID-19-related tweets from February 1, 2020, to April 30, 2022. We curated a hierarchical symptom lexicon for social media containing 10 affected organs/systems, 257 symptoms, and 1808 synonyms. The dynamic characteristics of COVID-19 symptoms over time were analyzed from the perspectives of weekly new cases, overall distribution, and temporal prevalence of reported symptoms. The symptom evolutions between virus strains (Delta and Omicron) were investigated by comparing the symptom prevalence during their dominant periods. A co-occurrence symptom network was developed and visualized to investigate inner relationships among symptoms and affected body systems.ResultsThis study identified 201 COVID-19 symptoms and grouped them into 10 affected body systems. There was a significant correlation between the weekly quantity of self-reported symptoms and new COVID-19 infections (Pearson correlation coefficient=0.8528; P<.001). We also observed a 1-week leading trend (Pearson correlation coefficient=0.8802; P<.001) between them. The frequency of symptoms showed dynamic changes as the pandemic progressed, from typical respiratory symptoms in the early stage to more musculoskeletal and nervous symptoms in the later stages. We identified the difference in symptoms between the Delta and Omicron periods. There were fewer severe symptoms (coma and dyspnea), more flu-like symptoms (throat pain and nasal congestion), and fewer typical COVID symptoms (anosmia and taste altered) in the Omicron period than in the Delta period (all P<.001). Network analysis revealed co-occurrences among symptoms and systems corresponding to specific disease progressions, including palpitations (cardiovascular) and dyspnea (respiratory), and alopecia (musculoskeletal) and impotence (reproductive).ConclusionsThis study identified more and milder COVID-19 symptoms than clinical research and characterized the dynamic symptom evolution based on 400 million tweets over 27 months. The symptom network revealed potential comorbidity risk and prognostic disease progression. These findings demonstrate that the cooperation of social media and a well-designed workflow can depict a holistic picture of pandemic symptoms to complement clinical studies.

Project description:ObjectivesLarge language models (LLMs) have demonstrated remarkable success in natural language processing (NLP) tasks. This study aimed to evaluate their performances on social media-based health-related text classification tasks.Materials and methodsWe benchmarked 1 Support Vector Machine (SVM), 3 supervised pretrained language models (PLMs), and 2 LLMs-based classifiers across 6 text classification tasks. We developed 3 approaches for leveraging LLMs: employing LLMs as zero-shot classifiers, using LLMs as data annotators, and utilizing LLMs with few-shot examples for data augmentation.ResultsAcross all tasks, the mean (SD) F1 score differences for RoBERTa, BERTweet, and SocBERT trained on human-annotated data were 0.24 (±0.10), 0.25 (±0.11), and 0.23 (±0.11), respectively, compared to those trained on the data annotated using GPT3.5, and were 0.16 (±0.07), 0.16 (±0.08), and 0.14 (±0.08) using GPT4, respectively. The GPT3.5 and GPT4 zero-shot classifiers outperformed SVMs in a single task and in 5 out of 6 tasks, respectively. When leveraging LLMs for data augmentation, the RoBERTa models trained on GPT4-augmented data demonstrated superior or comparable performance compared to those trained on human-annotated data alone.DiscussionThe results revealed that using LLM-annotated data only for training supervised classification models was ineffective. However, employing the LLM as a zero-shot classifier exhibited the potential to outperform traditional SVM models and achieved a higher recall than the advanced transformer-based model RoBERTa. Additionally, our results indicated that utilizing GPT3.5 for data augmentation could potentially harm model performance. In contrast, data augmentation with GPT4 demonstrated improved model performances, showcasing the potential of LLMs in reducing the need for extensive training data.ConclusionsBy leveraging the data augmentation strategy, we can harness the power of LLMs to develop smaller, more effective domain-specific NLP models. Using LLM-annotated data without human guidance for training lightweight supervised classification models is an ineffective strategy. However, LLM, as a zero-shot classifier, shows promise in excluding false negatives and potentially reducing the human effort required for data annotation.

Dataset Information

Identifying the effects of social media on health behavior: Data from a large-scale online experiment.

Publications

Identifying the effects of social media on health behavior: Data from a large-scale online experiment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets