Text and data mining (TDM) is the process of using automated techniques to derive information from large sets of digital content. Librarians who liaise with a wide range of academic disciplines need TDM skills to support research at their institutions.
Text and Data Mining Literacy for Librarians collects ways that academic libraries are supporting TDM literacy through services, workflows, and professional development. In five parts, it offers a variety of perspectives, insights, and experiences that can help you address the challenges of supporting TDM research, fit it into your existing reference and instruction work, and conduct your own.
- Essentials of Text and Data Mining (TDM) Literacy
- Data Literacy, Licensing, and Management Challenges with TDM
- TDM Research in Action: Practical Applications and Case Studies
- Generating Insights from Library Reference Data
- Proprietary TDM Software: Examples and Implementations
Chapters cover a range of disciplines and subject areas from a variety of institution sizes and types.
Text and Data Mining Literacy for Librarians is intended to empower library workers, inform decision-makers, and support our research communities as working with textual data becomes further embedded into the research landscape.
Whitney Kramer is the research and data librarian at Catherwood Library at Cornell University. In this role, she supports students and faculty in the School of Industrial and Labor Relations, and the Economics, and Statistics and Data Science departments who work with both structured and unstructured data. Her research interests include data literacy and the usage of text data in social science research. Her work has been published in the Data Literacy Cookbook, CHOICE, the Journal of New Librarianship, and ResearchDataQ. Previously, she was the entrepreneurship and public services librarian at the Roanoke Public Libraries in Roanoke, Virginia, and the business research librarian at Lippincott Library at the University of Pennsylvania.
Iliana Burgos is the emerging data practices librarian at Digital Scholarship Services at Cornell University Library. She supports researchers in exploring digital and computational approaches to humanities scholarship. Burgos specializes in text data management and computational text analysis methods guided by open scholarship principles. A Ronald E. McNair Scholar and American Library Association Spectrum Scholar, her research engages text data and algorithmic literacies, critical platform studies, and community-based data justice movements. She previously worked in community outreach roles as a Carolina Academic Library associate at the University of North Carolina at Chapel Hill and the Wilmington Institute Free Library of Delaware.
Evan Muzzall, PhD, is a formally trained forensic anthropologist and bioarchaeologist. He was a leader in various data science, anthropology, and humanities teaching and consulting settings for a decade at San Francisco State University, UC Berkeley, and Stanford University. He has also published machine learning and statistical modeling applications in top scientific journals and presently consults for the high-voltage electrical grid construction industry.
