<ul><li>Understanding patient feedback is crucial for improving healthcare services, yet analyzing unlabeled short-text feedback presents significant challenges due to limited data and domain-specific nuances.</li><li>This study explores unsupervised methods to extract meaningful topics from patient feedback collected from a healthcare system in Wisconsin, USA.</li><li>The study employed a keyword-based filtering approach and explored various topic modeling methods, including LDA, GSDMM, and BERTopic.</li><li>The integration of BERT embeddings with k-means clustering, called kBERT, outperformed other models, achieving high coherence and distinct topic separation in short-text healthcare feedback analysis.</li></ul>

Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement

Discover more