Abstract：Using Machine Learning and Natural Language Processing to Analyze Library Chat Reference Transcripts The use of artificial intelligence and machine learning has rapidly become a standard technology across all industries and businesses for gaining insight and predicting the futureIn recent yearsthe library community has begun looking at ways to improve library services by applying AI and machine learning techniques to library dataChat reference in libraries generates a large amount of data in the form of transcriptsThis study uses machine learning and natural language processing methods to analyze one academic librarys chat transcripts over a period of eight yearsThe built machine learning model tries to classify chat questions into a category of reference or nonreference questionsThe purpose is to predict the category of future questions by the model with the hope that incoming questions can be channeled to appropriate library departments or staffConsulting ServiceThis study specially pays special attention to the chat reference service in the library to try to predict the classification of future issues so that it can be transferred to the appropriate library department or personnelMachine LearningThis study uses machine learning methods to analyze the chat records of academic librariesThe purpose is to build a model that can classify the chat problem as a reference or non-reference problemNLPnatural language processingSince the research data is a library chat historythe natural language processing method is used when analyzing these records