Using Noisy Self-Reports to Predict Twitter User Demographics
This addresses the lack of annotated demographic data for social media platforms, which is a problem for computational social science researchers, though it is incremental as it builds on existing inference methods.
The paper tackled the problem of inferring race and ethnicity on Twitter by developing a method to identify self-reports from profile descriptions, resulting in models with good performance on gold standard survey data and enabling large-scale training resources.
Computational social science studies often contextualize content analysis within standard demographics. Since demographics are unavailable on many social media platforms (e.g. Twitter) numerous studies have inferred demographics automatically. Despite many studies presenting proof of concept inference of race and ethnicity, training of practical systems remains elusive since there are few annotated datasets. Existing datasets are small, inaccurate, or fail to cover the four most common racial and ethnic groups in the United States. We present a method to identify self-reports of race and ethnicity from Twitter profile descriptions. Despite errors inherent in automated supervision, we produce models with good performance when measured on gold standard self-report survey data. The result is a reproducible method for creating large-scale training resources for race and ethnicity.