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…

This study uses virtual reference transcripts for which patrons completed exit surveys to seek any correlations between user and librarian satisfaction within virtual reference transactions. By analyzing transcripts with a focus on three elements-technology performance, preferred reference practices, and the demonstrated communication levels of…