- This event has passed.
Seminar Series: Text Mining in Literature
March 16 @ 2:00 pm – 3:00 pm
Kim Nimon, PhD, is Professor in the Department of Human Resource Development (HRD) at The University of Texas at Tyler and Director of the Office of Research and Scholarship’s Research Design and Data Analysis Lab. Dr. Nimon’s expertise spans employee engagement, research design, and analytical methodologies. She currently serves as External Evaluator for two National Science Foundation (NSF) grants and has previously served as principal investigator or External Evaluator for six additional NSF projects.
Location: Blocker 220 and Zoom
Zoom ID: 974 9688 4861
Passcode: 923446
Text Mining HRD Research: Tools for Extracting and Discovering Themes in Literature
Systematic literature reviews are essential for advancing knowledge in Human Resource Development (HRD), yet the process of locating, extracting, and synthesizing information across large bodies of academic articles can be time-intensive. Advances in text mining and generative AI provide new opportunities to augment these processes while improving transparency and replicability. This seminar introduces two Shiny web applications designed to support text-mining–assisted literature review workflows in HRD research.
The first application, xtract, uses a Generative AI model to extract and organize structured information from academic articles. The session demonstrates a three-step workflow: (1) defining extraction fields and prompts, (2) uploading article text, and (3) generating structured outputs that facilitate synthesis across studies. By automating repetitive extraction tasks while applying consistent criteria, xtract improves the efficiency and reproducibility of systematic reviews. The second application, TopicMine, applies Latent Dirichlet Allocation (LDA) topic modeling to perform text mining on extracted article content. TopicMine helps researchers identify themes, patterns, and emerging topics across HRD and related scholarly literature. This seminar will illustrate how AI-assisted extraction and topic modeling can complement traditional literature review methods. Participant feedback will inform continued development of these tools to support more scalable, transparent, and rigorous research synthesis in HRD.