Social media reviews as a supplement to traditional quality survey in the Canadian context
Bibliographic record
Abstract
Measurement for quality improvement in health care can be difficult. Measuring patientcentred care ensures both patient, health care professionals and health system perspectives are accounted for. Unfortunately, obtaining meaningful data is challenging as traditional surveys, while necessary for longitudinal comparison, often fail to capture the changing perspectives of patients. The use of natural language processing to mine free-text reviews can supplement data obtained from traditional quality surveys and identify new areas of concern that patients find important. This work used natural language processing of Google user reviews of hospitals in British Columbia to identify topics relevant to the Canadian Patient Experience Survey – Inpatient Care (CPES-IC) and topics that the CPES-IC did not contain. The results also compared the output from computer-coded topics to ones that were manually identified. Of the 23 topics in the CPES-IC, six in the computer-coded and manual analyses were not found. Seventeen topics not in the CPES-IC were found in the computer-coded analysis, whereas 23 topics were identified in the manual coding. Of the newly identified topics, 12 were shared between the manual and computer-coded analyses. The implications of utilizing computers to make data readily accessible can improve decision-makers' ability to access data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.056 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.018 | 0.023 |
| Science and technology studies | 0.004 | 0.001 |
| Scholarly communication | 0.005 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".