The Value of Social Media Language for the Assessment of Wellbeing: A Systematic Review and Meta-Analysis

Wellbeing is an important concept that concerns researchers, policy makers, and the broader general public. The measurement of individuals’ wellbeing levels has predominantly been done through self-reports (e.g., survey questionnaires), which is time-consuming for respondents and costly. Alternatively, wellbeing can be measured in real-time by automatically analysing the language expressed on social media platforms (e.g., Facebook, Twitter, Weibo), through social media language text mining (SMTM). The application of this method for the measurement of wellbeing is relatively new, therefore the validity of SMTM for wellbeing is still being established. We present a systematic review based on 45 studies, and a meta-analysis on 32 effect sizes from a subset of 18 studies reporting correlations between SMTM wellbeing and survey-based ground truth measures. Our qualitative synthesis of the reviewed studies provided insights into current patterns in the literature including (1) most studies were conducted in English speaking samples, (2) Twitter was the most popular social media platform for data collection, (3) closed vocabulary dictionary methods driven and word-level methods of analysis were equally preferred, (5) satisfaction with life was the most popular ground-truth measure across the studies. In addition to this, our qualitative synthesis provided support for the face validity of SMTM for wellbeing by comparing/highlighting the similarities between the broader survey-based wellbeing literature and the findings of the SMTM-based wellbeing studies. Our meta-analysis found that SMTM shows convergent validity with traditional wellbeing measures (r = .54, 95% CI [.37, .67] for location level studies, and r = .33, 95% CI [.25, .40] for individual-level assessments).SMTM is a promising and growing method, but researchers should be aware of its current pitfalls such as the non-representativeness of the samples acquired through social media platforms. We provide recommendations for future SMTM studies in the context of wellbeing.