Objectives: Identifying thematic trends in published research can allow investigators to understand what questions or topics have been prioritized for dissemination over time and identify trends and directions for future studies. We aimed to define the most common research topics published in Gynecologic Oncology over a thirty-year period using an unsupervised machine-learning approach of topic modeling and subsequently discuss the trends of these topics over time. Methods: We retrieved the abstracts of all original research published in Gynecologic Oncology from 1990 to 2020 using PubMed. The abstract text was pre-processed into root words called tokens. The corpus of text was then run through the most popular topic modeling algorithm, Latent Dirichlet Allocation, to cluster the text into unnamed topical themes. Topics were then manually named by three independent reviewers. Named topics were subsequently investigated for temporal trends. Results: We retrieved 12,586 original research articles, of which 11,217 were evaluable for subsequent analysis. Twenty-three research topics were identified at the completion of topic modeling. The topics of basic science genetics, epidemiologic methods, and chemotherapy experienced the greatest increase over the time period, while surgical outcomes, reproductive age cancer management, and cervical dysplasia experienced the greatest decline. Interest in basic science research remained relatively constant. [Display omitted] Conclusions: The use of topic modeling, generated through an unsupervised machine learning approach, can allow investigators to identify trends in research themes and can be used to provide insight into the evolution of the field of gynecologic oncology research over time. [ABSTRACT FROM AUTHOR]