Social media reviews as a supplement to traditional quality survey in the Canadian context
Date
2021-09-13
Authors
Talusan, Christopher
Journal Title
Journal ISSN
Volume Title
Publisher
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.