Computational social science using topic modeling: Analyzing patients' values using a large hospital survey

Abstract

In this paper, we explore new approaches for combining manual and automatic content analysis. We compare three approaches to topic modelling: Latent Semantic Analysis (LSA), Latent Dirichlet Allocation (LDA), and Hierarchical Dirichlet Process (HDP). We applied all three approaches to study a corpus of 21,085 free‐response answers to questions from the Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) survey. We built topic models using the algorithms. Our preliminary results indicate that LSA and LDA yielded more useful results than HDP. We thematically analyzed the topic models and found similarities and differences in the factors that influenced patients' satisfaction with doctors and nurses.

Social-Child-Case Document Clustering based on Topic Modeling using Latent Dirichlet Allocation

“…The use of topic modeling approach in providing a useful view from a text collection has been done widely in various domains and cases. For example are, in journalism [9], information science [10] [11], and academic field [12]. Meanwhile, some researchers [13]- [15] have tried to use topic modeling for text clustering.…”