Academic Journal
What Single-Topic Summaries Miss in Hospital Reviews-Aspect-Level Evaluative Structure Using Generative Pretrained Transformer-Based Sentiment Analysis: Content Analysis.
| Τίτλος: | What Single-Topic Summaries Miss in Hospital Reviews-Aspect-Level Evaluative Structure Using Generative Pretrained Transformer-Based Sentiment Analysis: Content Analysis. |
|---|---|
| Συγγραφείς: | Hsueh JT; National Kaohsiung Normal University, Kaohsiung, Taiwan., Hsu SH; Department of Business Administration, Chung Hua University, Hsinchu, Taiwan.; Center for Continuing Education, National Tsing Hua University, Hsinchu, Taiwan., Chiu SF; College of Management, Chung Hua University, Hsinchu, Taiwan.; President's Office, Dachien General Hospital, Miaoli, Taiwan. |
| Πηγή: | Journal of medical Internet research [J Med Internet Res] 2026 Sep 14; Vol. 28, pp. e92325. Date of Electronic Publication: 2026 Sep 14. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: JMIR Publications Country of Publication: Canada NLM ID: 100959882 Publication Model: Electronic Cited Medium: Internet ISSN: 1438-8871 (Electronic) Linking ISSN: 14388871 NLM ISO Abbreviation: J Med Internet Res Subsets: MEDLINE |
| Imprint Name(s): | Publication: <2011- > : Toronto : JMIR Publications Original Publication: [Pittsburgh, PA? : s.n., 1999- |
| Ιατρικοί όροι (MeSH): | Hospitals* , Quality of Health Care*, Humans ; Taiwan |
| Περίληψη: | Background: Health care service quality is inherently multidimensional; yet, the dominant practice in applied text analysis assigns each patient review to a single topic via Latent Dirichlet Allocation (LDA). This simplification may systematically compress evaluative information when patients discuss multiple service dimensions with varying sentiments within the same review. Objective: This study compared the dominant-topic operationalization commonly used in applied LDA research with Generative Pretrained Transformer (GPT)-based aspect-based sentiment analysis (ABSA) to examine (1) the extent to which patient reviews contain multiple service-quality aspects and how single-topic summaries represent or obscure this structure, (2) the prevalence and patterning of mixed-sentiment reviews, and (3) whether positive and negative reviews differ in aspect comention profiles, before and after adjusting for marginal aspect prevalence. Methods: We analyzed 5467 Google Reviews posted in 2024 from all 24 medical centers in Taiwan. LDA (K=7 topics) and GPT-based ABSA with structured prompts were applied to the same corpus, with the 7 ABSA categories aligned to the LDA topic labels for a controlled but information-asymmetric comparison. Two independent annotators achieved interrater reliability of Cohen κ=0.82; against the consensus gold standard, GPT-4o achieved an accuracy of 0.89, a weighted F Results: Aspect-bearing reviews discussed an average of 2.05 distinct aspects (95% bootstrap CI 2.02-2.08), yielding an illustrative 51.2% representational compression estimate under dominant-topic assignment (95% bootstrap CI 50.6%-51.9%). A soft-assignment LDA baseline reduced count-level compression to 1.7%, but semantic alignment with ABSA aspects remained limited (mean set Jaccard=0.33), and topic assignments carry no aspect-level sentiment polarity. Among multiaspect reviews, 11.0% exhibited cross-aspect mixed sentiment, with Technical-Functional Divergence-praising technical quality while criticizing functional quality-appearing in 61.6% of these cases. Clinical dimensions were more frequently comentioned in positive reviews and operational dimensions in negative reviews; however, pointwise mutual information analysis indicated that these differences were substantially confounded with marginal aspect prevalence rather than reflecting differential co-occurrence tendencies. Conclusions: In this corpus, dominant-topic assignment compressed multiaspect patient feedback; soft-assignment LDA recovered topic counts but did not restore semantic alignment or aspect-level sentiment polarity. A nontrivial subset of reviews exhibited cross-aspect mixed sentiment, most commonly praising clinical competence while criticizing functional service dimensions, and positive and negative reviews discussed different constellations of quality dimensions-differences that primarily reflect which aspects patients discuss rather than prevalence-independent associations. Aspect-level analysis that preserves both multidimensional structure and sentiment polarity may help organize patient feedback at a more diagnostically specific level than single-topic summaries. (©Jung-Tang Hsueh, Sheng-Hsun Hsu, Shwu-Fen Chiu. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 14.09.2026.) |
| References: | BMC Health Serv Res. 2021 Apr 9;21(1):326. (PMID: 33836737) IEEE J Biomed Health Inform. 2026 Apr 14;PP:. (PMID: 41979957) J Biomed Inform. 2021 Aug;120:103844. (PMID: 34153432) PLoS One. 2025 Mar 18;20(3):e0313442. (PMID: 40100826) BMJ Qual Saf. 2013 Mar;22(3):251-5. (PMID: 23349387) J Med Internet Res. 2013 Feb 01;15(2):e24. (PMID: 23372115) JMIR AI. 2026 Mar 12;5:e90759. (PMID: 41818631) Cad Saude Publica. 2015 Jan;31(1):11-25. (PMID: 25715288) Artif Intell Med. 2019 Nov;101:101727. (PMID: 31813490) JAMA. 1988 Sep 23-30;260(12):1743-8. (PMID: 3045356) Healthcare (Basel). 2022 Oct 05;10(10):. (PMID: 36292392) |
| Contributed Indexing: | Keywords: Taiwan; hospitals; machine learning; natural language processing; patient satisfaction; quality of health care; sentiment analysis; text mining |
| Entry Date(s): | Date Created: 20260914 Date Completed: 20260914 Latest Revision: 20261001 |
| Update Code: | 20261001 |
| PubMed Central ID: | PMC13620426 |
| DOI: | 10.2196/92325 |
| PMID: | 42735401 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1438-8871 |
|---|---|
| DOI: | 10.2196/92325 |