用上下文嵌入聚类法挖掘医疗反馈中的主题，提升分析效果。
Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement
- 结合BERT嵌入与k-means聚类，提出kBERT方法处理短文本。
- 在439条反馈中实现最高主题一致性（Cv=0.53）和分离度（IRBOavg=1.00）。
- 适合医疗数据分析人员用于无标注反馈的主题挖掘。
理解患者反馈对改进医疗服务至关重要，但未标注的短文本反馈因数据有限且领域特征明显，分析难度大。传统监督方法需大量标注数据，因此无监督方法更实用。本研究分析了美国威斯康星州一家医疗系统的439份调查反馈。采用领域词典过滤出投诉相关文本。评估了传统主题模型（如LDA、GSDMM）与基于神经嵌入的BERTopic方法。为提升稀疏短文本的连贯性与可解释性，提出kBERT方法，融合BERT嵌入与k-means聚类。通过一致性得分（Cv）和平均逆排名偏倚重叠（IRBOavg）评估性能。kBERT在所有模型中表现最优，达最高一致性（Cv=0.53）与最佳主题分离度（IRBOavg=1.00）。结果表明，上下文感知的嵌入模型在医疗数据分析中具有显著价值。
原文摘要 · Abstract (English)
Understanding patient feedback is crucial for improving healthcare services, yet analyzing unlabeled short-text feedback presents challenges due to limited data and domain-specific nuances. Traditional supervised approaches require extensive labeled datasets, making unsupervised methods more practical for extracting insights. This study applies unsupervised techniques to analyze 439 survey responses from a healthcare system in Wisconsin, USA. A keyword-based filter was used to isolate complaint-related feedback using a domain-specific lexicon. To identify dominant themes, we evaluated traditional topic models such as Latent Dirichlet Allocation (LDA) and Gibbs Sampling Dirichlet Multinomial Mixture (GSDMM) -- alongside BERTopic, a neural embedding-based clustering method. To improve coherence and interpretability in sparse, short-text data, we propose kBERT, which integrates BERT embeddings with k-means clustering. Model performance was assessed using coherence scores (Cv ) and average Inverted Rank-Biased Overlap (IRBOavg). kBERT achieved the highest coherence (Cv = 0.53) and topic separation (IRBOavg = 1.00), outperforming all other models. These findings highlight the value of embedding-based, context-aware models in healthcare analytics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。