As a music reference librarian at the Library of Congress, Cait Miller gets obscure songs questions that pose greater issues for music librarians because music libraries are generally searchable by format, genre, instrumentation, composer, and/or title but not often by lyrical quotation. New crowdsourcing transcription programs, however, give hope…

This study aims to evaluate the effectiveness and potential utility of using machine learning and natural language processing techniques to develop models that can reliably predict the relative difficulty of incoming chat reference questions. Using a relatively large sample size of chat transcripts (N = 15,690), an empirical experimental design…

In the five years following implementation of a chat reference service at James Madison University (JMU), the service proved very popular but was not closely assessed for quality of service. Using grounded theory and qualitative data analysis techniques, a comprehensive assessment effort was begun in earnest and is in progress. Preliminary results…