Knowledge Structure and Research Trends in Korean Voice Disorder Research During the COVID-19 Pandemic and Post-Pandemic Period: A Text Mining and Network Analysis

Background: Voice disorders have become an important healthcare issue owing to advances in artificial intelligence (AI) and digital healthcare. Although AI-related studies have rapidly increased, little is known about how research topics and knowledge structures have evolved during the COVID-19 pandemic and the post-pandemic period. This study investigated changes in Korean voice disorder research across these two periods. Methods: Bibliographic data were collected from the Research Information Sharing Service (RISS) and analyzed using TEXTOM V6.0. Frequency analysis, term frequency–inverse document frequency (TF-IDF), degree centrality, ego network analysis, convergence of iterated correlations (CONCOR), and the Louvain clustering detection algorithm were performed to identify major keywords, knowledge structures, and thematic clusters. Results: A total of 5332 records were analyzed, including 2818 from the pandemic period and 2514 from the post-pandemic period. The keywords “voice,” “disorder,” and “research” remained dominant throughout both periods. Degree centrality for “voice” increased from 47.52 to 50.07, while “research” increased from 39.76 to 42.17. AI-related keywords, including “recognition,” “application,” “foundation,” and “accessibility,” became more prominent after the pandemic. CONCOR and Louvain analyses revealed a shift from conventional clinical research toward AI-enabled digital healthcare and intelligent rehabilitation. Conclusions: Korean voice disorder research has evolved into a multidisciplinary, AI-driven field. These findings provide quantitative evidence of changing knowledge structures and may guide future AI-based voice disorder research and rehabilitation.