The Upworthy Research Archive is an open dataset of thousands of A/B tests of headlines conducted by Upworthy from January 2013 to April 2015. At the time of release, it is the largest open-access collection of randomized behavioral studies openly available for research and education.
For more details, see the [Upworthy Reseach Archive Homepage](https://upworthy.natematias.com/).
A data descriptor of the archive has been published by Scientific Data here:
* Matias, J., Munger, K., Aubin Le Quere, M., Ebersole, C. (2021) **[The Upworthy Research Archive, a time series of 32,487 experiments in U.S. media](https://doi.org/10.1038/s41597-021-00934-7).** Scientific Data.
In June 2024, the team published an update to the archive that documents randomization balance problems in 22% of the A/B tests in the dataset. These have been labeled and the Data Descriptor has been updated. See this page for more details:
* [Ensuring Reliable Science from Platform A/B Test Archives - an Update to the Upworthy Archive](https://upworthy.natematias.com/2024-06-upworthy-archive-update)