Yale University Library has received a National Leadership Grant from the Institute of Museum and Library Services (IMLS) for Improving Search and Discovery of Digital Resources Using Topic Modeling, a unique research project that will attempt to improve the search and discovery of digital resources. The project will leverage the enormous textual output from mass digitization efforts and the popularity of social tagging to improve the searchability and usability of digital library and museum collections. Partners in the project include the University of Michigan and the University of California, Irvine.
Topic modeling is a relatively new automated text mining technique that can be used to extract semantic topics from any large collection of text items. These semantic topics can be highly useful as subjects and can be used to improve access to resources with little or no descriptive metadata.
Project investigators will apply topic modeling to three important classes of digital library resources: full-text books; images with descriptive metadata; and tagged images. After running the topic model on each collection of objects, domain experts will interpret the automatically learned topics and will evaluate their usefulness as subjects. The project team will develop user interface applications that implement learned topics and will assess their effectiveness in improving search and discovery. To broaden the impact of the work, topic modeling software, tools, and course materials will be made available in workshops and on the project web site. More information on the project can be found on the IMLS’s web site.
The Institute of Museum and Library Services is the primary source of federal support for the nation’s 122,000 libraries and 17,500 museums. The Institute's mission is to create strong libraries and museums that connect people to information and ideas. The Institute works at the national level and in coordination with state and local organizations to sustain heritage, culture, and knowledge; enhance learning and innovation; and support professional development.