Can social media reliably estimate unemployment?
Do Lee, Manuel Tonneau, Boris Sobol, Nir Grinberg, Samuel P Fraiberger, Yucheng Zhang · 2025
Read Can social media reliably estimate unemployment? by Do Lee, Manuel Tonneau, Boris Sobol, Nir Grinberg, Samuel P Fraiberger, Yucheng Zhang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12750448.txt.
Description
Lee and five co-authors test whether social media can track joblessness in work from twenty twenty-five. Online traces offer fast signals for policy, but their trust is often doubted. Official surveys are slower and can lag in a crisis.
Their method flags posts where people disclose losing a job, using a tuned AI model. They then adjust the counts with inferred user traits to match the population. The estimates beat the industry forecast average in their tests. They also improved forecasts of United States jobless claims up to two weeks early, at national, state, and city levels. The case shows online data can aid, not replace, surveys.
Catalog record
| CREATOR | Do Lee, Manuel Tonneau, Boris Sobol, Nir Grinberg, Samuel P Fraiberger, Yucheng Zhang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |