Jacob Hill, who joined Digital Library Systems and Services (DLSS) in October 2018 as Project and Data Manager for the Digital Library of the Middle East, has been promoted to a continuing role as Data Scientist. Please join me in congratulating Jacob!
In addition to ongoing operational and program support for the DLME (albeit at a reduced level), Jacob has new responsibilities in applying data science skills and methods to library data (such as analytics and various metadata) with the goal of powering, extending, and enhancing our established digital library services, the Libraries’ partnership projects, and the greater research enterprise at Stanford. This is an exciting development for DLSS and the library units we support.
Some of the areas where Jacob is already actively involved in this work include:
- Supporting Library Data Systems - Several of our library systems rely on data that is spread across other systems. One example is our archival data which is manually created in ArchivesSpace but needs to flow into ArcLight, the Online Archive of California, and Aeon. Some of these systems also require data that is not in ArchivesSpace. Jacob has been learning about this data flow and exploring opportunities for data remediation and enrichment, as well as automating staff processes that are currently manual.
- Applying Machine Learning Techniques to Library Collections - Through the Digital Library of the Middle East, Jacob has been exploring opportunities to apply machine learning techniques to IIIF collections, including optical character recognition (OCR) and handwritten text recognition (HTR) for Arabic and Persian texts. He is exploring these opportunities with an eye towards applying any learning to our internal collections.
- Serving as Technical Lead on Stanford Libraries’ Google Analytics - Jacob will also be the service manager for our web analytics with the intention of trying to leverage the data in Google Analytics to better understand usage of our online collections and to improve our discovery and access web applications.
- Participating in Research Intelligence Activities - Jacob has been working on several reports that leverage publication, funding, and internal university data to better understand the universities’ publishing practices. Examples include a university-wide open access report as well as shared facility publication reports that are required by funding agencies.
We will share more about the novel work with library data that Jacob will be undertaking. Stay tuned!