Assessing bias in migration stock estimates from Facebook and Instagram using a social media-based survey
Year: 2026
Type: report
Abstract: This study, conducted as part of the PREMIUM EU project, evaluates the reliability of Facebook and Instagram digital trace data for estimating migration and mobility patterns.Traditional migration data sources suffer from delays and limited granularity, while social media data offer real-time insights but raise concerns about representativeness and bias.We combine digital trace data from Meta's advertising platform with a novel online survey -the International Mobility Survey -targeting Polish migrants in the UK and Germany using Facebook and Instagram platforms.The survey collects detailed behavioral data including migration history, social media usage, and future mobility intentions, enabling direct comparisons with platform-derived estimates.Our methodology employs post-stratification weighting to enhance representativeness, using three approaches to address sparse data: age-sex aggregation, Generalized Additive Models, and imputation techniques.The results identify various biases in Meta's platform data.These findings help improve existing migration estimation models that combine digital and traditional data sources.
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
SDG: Reduced inequalities
Open Access status: gold
OpenAlex ID: W7162452766