Chatbots in the library: is it time?
This paper aims to describe a pilot at the University of Nebraska-Lincoln for a chatbot that answers questions about the library and library resources.
The chatbot was developed using a SQL database to store the question and answers using artificial intelligence mark-up language metadata. The user interface was built using PHP, adapted from Program-O. The open source PHP program was modified to support better display and the launching of URLs within the chatbot screen. Database content was created by “mining” library websites for information, and analyzing chat logs.
The chatbot answers questions from a variety of users from around the world. It has attracted an unexpected number of social chatters, which required some additional metadata to accommodate personal chatting and to guide questions back to the intent of the project. The majority of questions are directional or factual questions that Pixel can handle. The database proved to be practical to build and revise as library resources and personnel changed.
The chatbot provides a 24 hour, seven day a week service that is consistent, can be enhanced as resources, services, or staff change, and provides a playful interface that engages users. It replaces complicated navigation systems and scrolling through search results with more targeted answers, and has the ability to refer questions to librarians.
Although chatbots have been around for several decades, there is a scarcity of reports in published library literature about their use in libraries.