Dataset Information

Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods.

ABSTRACT: Researchers and policy makers worldwide are interested in measuring the subjective well-being of populations. When users post on social media, they leave behind digital traces that reflect their thoughts and feelings. Aggregation of such digital traces may make it possible to monitor well-being at large scale. However, social media-based methods need to be robust to regional effects if they are to produce reliable estimates. Using a sample of 1.53 billion geotagged English tweets, we provide a systematic evaluation of word-level and data-driven methods for text analysis for generating well-being estimates for 1,208 US counties. We compared Twitter-based county-level estimates with well-being measurements provided by the Gallup-Sharecare Well-Being Index survey through 1.73 million phone surveys. We find that word-level methods (e.g., Linguistic Inquiry and Word Count [LIWC] 2015 and Language Assessment by Mechanical Turk [LabMT]) yielded inconsistent county-level well-being measurements due to regional, cultural, and socioeconomic differences in language use. However, removing as few as three of the most frequent words led to notable improvements in well-being prediction. Data-driven methods provided robust estimates, approximating the Gallup data at up to r = 0.64. We show that the findings generalized to county socioeconomic and health outcomes and were robust when poststratifying the samples to be more representative of the general US population. Regional well-being estimation from social media data seems to be robust when supervised data-driven methods are used.

SUBMITTER: Jaidka K

PROVIDER: S-EPMC7229753 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods.

Jaidka Kokil K Giorgi Salvatore S Schwartz H Andrew HA Kern Margaret L ML Ungar Lyle H LH Eichstaedt Johannes C JC

Proceedings of the National Academy of Sciences of the United States of America 20200427 19

Researchers and policy makers worldwide are interested in measuring the subjective well-being of populations. When users post on social media, they leave behind digital traces that reflect their thoughts and feelings. Aggregation of such digital traces may make it possible to monitor well-being at large scale. However, social media-based methods need to be robust to regional effects if they are to produce reliable estimates. Using a sample of 1.53 billion geotagged English tweets, we provide a s ...[more]

PMID: 32341156

Similar Datasets

Project description:Research on children's quality of life and subjective well-being has advanced over the past decade largely as a result of developments in childhood theory, children's rights legislation, and the shift toward positive social science. However, in line with the uncertainty regarding the conceptualization of subjective well-being, the structural configuration of children's subjective well-being has not been considered in the literature. In the current study, we present and test a model of children's subjective well-being, which includes global (context-free items assessing overall and general well-being, without reference to a specific aspect of life) and specific (domain-based items assessing a specific aspect of life) cognitive components, and positive and negative affect. We further test the fit structure of a hierarchical structural (second-order) model of children's subjective well-being. Finally, we test the measurement invariance of the hierarchical model across age and gender. We use data from the third Wave of the Children's Worlds Survey. The data source includes a sample of 92,782 participants selected from 35 countries (girls = 49.7%) in two age groups (10- and 12-years-old). We found a good fit for the four-factor confirmatory factor model of children's subjective well-being. Correlations between the various latent factors were as anticipated-with positive correlations between the life satisfaction components and positive affect, and negative correlations with negative affect. We further found a good fit for the hierarchical structural model of children's subjective well-being. Finally, we found the tenability of measurement invariance across age and gender. The study extends the generalizability of the hierarchical structural configuration of the subjective well-being to child samples, and provides a viable model to explore correlates and predictors of children's subjective well-being using the full conceptual model. Finally, we propound the tenability of a quadripartite hierarchical conceptual model of children's subjective well-being.

Project description:BackgroundOne important aspect of subjective judgments about one's well-being (i.e., subjective well-being: life satisfaction, positive affect, and negative affect) is that cultural features, such as, nationality seem to shape cognitive judgments about the "the ideal life." In this comparative study we examined differences in subjective well-being and psychological well-being between Italian and Swedish adolescents and tested if the relationship between the three constructs of subjective well-being (i.e., satisfaction with life, positive affect, and negative affect) and psychological well-being was moderated by the adolescents' nationality.MethodItalian (n = 255) and Swedish (n = 277) adolescents answered to the Satisfaction with Life Scale, the Positive Affect Negative Affect Schedule, and Ryff's Scales of Psychological Well-Being. Differences between samples were tested using a Multiple Analysis of Variance. We also conducted a multiple group analysis (Italy and Sweden) using Structural Equation Modelling to investigate the relationship between all three subjective well-being constructs and psychological well-being.ResultsItalian adolescents scored significantly higher in satisfaction with life than Swedish adolescents. Additionally, across countries, girls scored significantly higher in negative affect than boys. In both countries, all three constructs of subjective well-being were significantly associated to adolescents' psychological well-being. Nevertheless, while the effect of the relationship between affect and psychological well-being was almost the same across countries, life satisfaction was more strongly related to psychological well-being among Swedish adolescents.ConclusionsThe present study shows that there are larger variations between these two cultures in the cognitive construct of subjective well-being than in the affective construct. Accordingly, associations between the cognitive component, not the affective component, of subjective well-being and psychological well-being differ between countries as well.

Project description:ObjectiveAs limitations in activities of daily living are major components of many stroke outcome scales, we examined how well activity limitations predicted subjective well-being among stroke survivors in a nationally representative survey.MethodsIndividuals with a self-reported history of stroke were identified from the National Health and Aging Trends Study. Subjective well-being (primary outcome) was assessed with a validated 7-item measure (higher = greater well-being) assessing emotions (cheerful, bored, full of life, and upset) and self-realization (purpose in life, self-acceptance, and environmental mastery). Activity limitations were defined by the receipt of help in any of 11 activities of daily living/instrumental activities of daily living. Multivariable linear regression assessed predictors of well-being including medical, physical, cognitive, psychological, and environmental factors.ResultsA total of 738 stroke survivors age 65 or older were included (57% female, 9% African American, 6% Hispanic). Activity limitations were modestly associated with well-being after adjusting for demographic characteristics and availability of assistance (estimate -0.49, 95% confidence interval -0.61 to -0.37). However, in the fully adjusted model (R2 = 0.28), neither activity limitations nor physical capacity was associated with subjective well-being. Predictors of lower well-being in the final model included depressive symptoms, chewing/swallowing problems, pain that limited activity, and restricted participation in valued life activities. Income and executive function were modestly associated with improved well-being, while comorbidities and communication technology access were not associated.ConclusionsActivity limitations were not associated with stroke survivors' subjective well-being after adjustment for other factors. While some predictors of well-being after stroke were identified, the determinants of well-being remained largely unexplained.

Dataset Information

Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods.

Publications

Estimating geographic subjective well-being from Twitter: A comparison of dictionary and data-driven language methods.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets