Dataset Information

Building a profile of subjective well-being for social media users.

ABSTRACT: Subjective well-being includes 'affect' and 'satisfaction with life' (SWL). This study proposes a unified approach to construct a profile of subjective well-being based on social media language in Facebook status updates. We apply sentiment analysis to generate users' affect scores, and train a random forest model to predict SWL using affect scores and other language features of the status updates. Results show that: the computer-selected features resemble the key predictors of SWL as identified in early studies; the machine-predicted SWL is moderately correlated with the self-reported SWL (r = 0.36, p < 0.01), indicating that language-based assessment can constitute valid SWL measures; the machine-assessed affect scores resemble those reported in a previous experimental study; and the machine-predicted subjective well-being profile can also reflect other psychological traits like depression (r = 0.24, p < 0.01). This study provides important insights for psychological prediction using multiple, machine-assessed components and longitudinal or dense psychological assessment using social media language.

SUBMITTER: Chen L

PROVIDER: S-EPMC5685571 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Building a profile of subjective well-being for social media users.

Chen Lushi L Gong Tao T Kosinski Michal M Stillwell David D Davidson Robert L RL

PloS one 20171114 11

Subjective well-being includes 'affect' and 'satisfaction with life' (SWL). This study proposes a unified approach to construct a profile of subjective well-being based on social media language in Facebook status updates. We apply sentiment analysis to generate users' affect scores, and train a random forest model to predict SWL using affect scores and other language features of the status updates. Results show that: the computer-selected features resemble the key predictors of SWL as identified ...[more]

PMID: 29135991

Similar Datasets

Project description:BackgroundSeveral large-scale studies and reviews have reported both negative and positive associations of social media use with well-being, suggesting that the findings are more complex and need more nuanced study. Moreover, there is little or no exploration of how social media use in adolescence influences flourishing, a more all-encompassing construct beyond well-being, including six sub-domains (i.e., happiness, meaning and purpose, physical and mental health, character, close social relationships, and financial stability). This paper aims to fill this gap by understanding how adolescents might flourish through social media activities by fulfilling the basic needs pointed out by the Self-Determination Theory, i.e., relatedness, autonomy, and competence.MethodsThe study is drawn on cross-sectional data collected from 1,429 Swiss adolescents (58.8% females, Mage = 15.84, SDage = 0.83) as part of the HappyB project in Spring 2022. Self-reported measures included the Harvard Adolescent Flourishing scale, positive and negative online social experiences, self-disclosure on social media, and social media inspiration. Control variables included, among others, self-esteem, ill-being, and personality.ResultsAfter applying Bonferroni's correction, results of the hierarchical regression analyses showed that positive social media experiences (β = 0.112, p < 0.001) and social media inspirations from others (β = 0.072, p < 0.001) and for others (β = 0.060, p = 0.003) were positively associated with flourishing. Flourishing was inversely associated with negative social media experiences (β = -0.076, p < 0.001). Among covariates, self-esteem (β = 0.350, p < 0.001), ill-being (β = -0.252, p < 0.001), perceived school environment (β = 0.138, p < 0.001), self-reported level of physical activity (β =0.109, p < 0.001), and perceived socio-economic status (β = -0.059, p = 0.001) were all related to flourishing. In contrast, gender, high school year, age, perceived stress, and personality (extraversion and neuroticism) were not.ConclusionUsing a well-being framework to investigate social media use in adolescents is needed to go beyond the ill-being perspective. Our results align with the needs pointed out by the Self-Determination Theory. Carrying out social media activities in a way that promotes-rather than diminishes-flourishing should be included as an additional good habit influencing adolescents' development. We suggest that interventions aiming to foster adolescents' flourishing should include curricula aiming to promote a good use of social media through positive online social relationships and inspirational contents.

Dataset Information

Building a profile of subjective well-being for social media users.

Publications

Building a profile of subjective well-being for social media users.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets