In 2015, the Research and Instructional Services Unit of Meyer Library at Missouri State University was challenged to update and rethink the current service model and space. We had been operating in a traditional reference model, including a large, walkup reference desk that was staffed primarily by faculty librarians. After reviewing the…

For decades, declines in library reference use have been inextricably tied to technological improvements. This article asserts that reference staffing models may be a significant predictor of a decline in reference questions. Using two years of data, collected from a large public university, the researchers determined user preferences among five…

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…