NASA's AI-Generated Metadata Tags — Machine-Learning Auto-Tagging for Federal Open Data Discovery

NASA's Scientific and Technical Information (STI) corpus spans scientific articles, technical reports, software repositories and other unstructured content scattered across multiple systems, historically tagged by hand with roughly ten keywords per document drawn from an evolving taxonomy of more than 20,000 standardized terms.
The STI team and NASA's OCIO Data Analytics Team built a machine-learning and NLP-based automated tagging system trained on the NASA Technical Reports Server's corpus of 3.5 million already-tagged documents, then released it as open-source software — the concept-tagging-training and concept-tagging-api repositories on GitHub — and documented it as a Federal Data Strategy 'proof point' case study (published May 2019).
The tool's use has since expanded beyond its original article-tagging purpose to other unstructured NASA data, and the case study frames it explicitly as a template other federal agencies can replicate on their own text. No public accuracy, usage or before/after discoverability figures have been published, so its measured impact on data findability remains undemonstrated even though the system has been operating for several years.

Read the full analysis: https://resources.data.gov/resources/fdspp-nasa-ai-metadata-tags/