Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912829608558592 |
|---|---|
| author | Islam, K M Sajjadul Karri, Ravi Teja Vegesna, Srujan Wu, Jiawei Madiraju, Praveen |
| author_facet | Islam, K M Sajjadul Karri, Ravi Teja Vegesna, Srujan Wu, Jiawei Madiraju, Praveen |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14068 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement Islam, K M Sajjadul Karri, Ravi Teja Vegesna, Srujan Wu, Jiawei Madiraju, Praveen Machine Learning Human-Computer Interaction 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. |
| title | Contextual Embedding-based Clustering to Identify Topics for Healthcare Service Improvement |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2504.14068 |