Working Papers

This paper proposes the use of synthetic training data generated by large language models
to improve machine learning SDG classifiers. It shows that supplementing existing training data with
synthetic data produced by the ChatGPT tool improves the performance of the SDGClassy classifier.
This addition of synthetic data is especially useful in building SDG classifiers given the limited availability
of properly labeled data and the complex, interconnected nature of the SDGs. Synthetic data thus enables
more effective machine-learning applications in this context.

Between the many resolutions, speeches, reports and other documents that are produced each year, the United Nations is awash in text. It is an ongoing challenge to create a coherent and useful picture of this corpus. In particular, there is an interest in measuring how the work of the United Nations system aligns with the Sustainable Development Goals (SDGs). There is a need for a scalable, objective, and consistent way to measure how similar any given publication is to each of the 17 SDGs. This paper explains a proof-of-concept process for building such a system using machine learning algorithms. By creating a model of the 17 SDGs it is possible to measure how similar the contents of…