University of North Texas (University of North Texas, University Libraries)

University of North Texas Libraries, partnering with the University of Illinois Chicago (UIC) Computer Science Department, will conduct a research project with the long-term objective of improving access to digital resources housed in web archives. The project team will investigate the potential of using existing bibliographic metadata related to state government document collections to better train machine learning models that can assist librarians and information professionals in identifying and classifying high-value publications from large web archives. The project team will share all datasets, algorithms, and tools resulting from this project through GitHub and the project webpage, and they will communicate research findings through publications and presentations at conferences on library science, information retrieval, artificial intelligence, and natural language processing. Subrecipient, UIC, will be responsible for the machine learning component of the project and will help disseminate research findings.