Purpose & Goals

Florida Gulf Coast University (FGCU) is a large public university with the basic Carnegie classification of “Doctoral/Professional Universities” and a student body that is 86% undergraduate. The University Library is supported by eight in-unit faculty librarians who perform both liaison and functional responsibilities including staffing the online chat “desk.” The University Library subscribes to Springshare and uses the LibChat platform. The service was launched in 2015 to serve as a supplement to a physical reference desk consultation model. The COVID-19 pandemic and associated closure of the FGCU campus led to the subsequent and, ultimately, permanent closure of the physical reference desk leaving students fewer options for librarian-facilitated research assistance. The librarians developed a marketing plan that resulted in a substantial increase in chat transactions. The purpose of the current investigation is to investigate the following questions:

• How did the pandemic impact patrons’ use of and experience using FGCU’s chat reference for research assistance?
• How to describe the change in quantity and type of chat questions before COVID-19, during COVID-19, and after COVID-19?

Design & Methodology

Chat transcripts from April 2015 through May 2023 were downloaded from the Springshare LibChat platform (IRB # 2022-38). The transcripts already include useful data such as the user’s name (if provided, anonymous, if not), referring URL, answerer’s name, timestamp, wait time, duration, rating, initial question, message count, and a full transcript of the chat. Although there is a category for tags, which would theoretically make the data analysis easier, FGCU librarians have not used that functionality. Because there is no organization of transactions into categories or tag groups, any classification of the data will need to be done retrospectively. Because the raw transcript data is primarily textual and would require an exorbitant amount of work to manually tag and process, it was decided to utilize textual analysis to process it. Based on the literature, there are several possible methods to analyze the data, including examples of sentiment analysis, word frequency, and topic modelling using tools such as R, NVivo, Voyant, and Python (Tasking and Al, 2019; Brousseau, Jonson, and Thacker, 2021; Koh and Fienup, 2021; Sharma, Barrett, and Stapelfeldt, 2022; Wang, 2022; Watson, 2023). FGCU librarians intend to use semi-supervised machine learning to analyze the chat data.

Conclusions

Through analysis of the chat transcripts, FGCU librarians hope to determine in what way online chat has supplemented or superseded in-person consultation services and whether the impact of the COVID-19 pandemic and the rise of artificial intelligence have led to new expectations of always-online assistance. Additional questions we hope to answer are:

• What interventions are needed to improve our online chat service?
• Should chat continue to be staffed by faculty librarians?
• How can student success be measured and improved upon?
• What role should artificial intelligence play in the future of the service and how should that be implemented?

Implications & Value

This study will contribute to the growing body of research using computational analysis for large, textual library chat datasets. In addition, it will enrich the conversation about the evolution of library consultation services and the role of the library in student success.