Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study
BackgroundPrevious studies have highlighted gender differences in web-based physician reviews; however, so far, no study has linked web-based ratings with quality of care. ObjectiveWe compared a consumer-generated measure of physician quality (web-based ratings) w...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2022-09-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2022/9/e34902 |
| _version_ | 1797734754724872192 |
|---|---|
| author | Julia Barnett Margrét Vilborg Bjarnadóttir David Anderson Chong Chen |
| author_facet | Julia Barnett Margrét Vilborg Bjarnadóttir David Anderson Chong Chen |
| author_sort | Julia Barnett |
| collection | DOAJ |
| description |
BackgroundPrevious studies have highlighted gender differences in web-based physician reviews; however, so far, no study has linked web-based ratings with quality of care.
ObjectiveWe compared a consumer-generated measure of physician quality (web-based ratings) with a clinical quality outcome (sanctions for malpractice or improper behavior) to understand how patients’ perceptions and evaluations of physicians differ based on the physician’s gender.
MethodsWe used data from a large web-based physician review website and the Federation of State Medical Boards. We implemented paragraph vector methods to identify words that are specific to and indicative of separate groups of physicians. Then, we enriched these findings by using the National Research Council Canada word-emotion association lexicon to assign emotional scores to reviews for different subpopulations according to gender, gender and sanction, and gender and rating.
ResultsWe found statistically significant differences in the sentiment and emotion of reviews between male and female physicians. Numerical ratings are lower and sentiment in text reviews is more negative for women who will be sanctioned than for men who will be sanctioned; sanctioned male physicians are still associated with positive reviews.
ConclusionsGiven the growing impact of web-based reviews on demand for physician services, understanding the different dynamics of reviews for male and female physicians is important for consumers and platform architects who may revisit their platform design. |
| first_indexed | 2024-03-12T12:49:02Z |
| format | Article |
| id | doaj.art-ec7cf2ed86f840348ec36528d1620276 |
| institution | Directory Open Access Journal |
| issn | 2561-326X |
| language | English |
| last_indexed | 2024-03-12T12:49:02Z |
| publishDate | 2022-09-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj.art-ec7cf2ed86f840348ec36528d16202762023-08-28T23:02:27ZengJMIR PublicationsJMIR Formative Research2561-326X2022-09-0169e3490210.2196/34902Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods StudyJulia Barnetthttps://orcid.org/0000-0002-3476-1110Margrét Vilborg Bjarnadóttirhttps://orcid.org/0000-0003-2955-1992David Andersonhttps://orcid.org/0000-0002-1128-6206Chong Chenhttps://orcid.org/0000-0002-4086-0000 BackgroundPrevious studies have highlighted gender differences in web-based physician reviews; however, so far, no study has linked web-based ratings with quality of care. ObjectiveWe compared a consumer-generated measure of physician quality (web-based ratings) with a clinical quality outcome (sanctions for malpractice or improper behavior) to understand how patients’ perceptions and evaluations of physicians differ based on the physician’s gender. MethodsWe used data from a large web-based physician review website and the Federation of State Medical Boards. We implemented paragraph vector methods to identify words that are specific to and indicative of separate groups of physicians. Then, we enriched these findings by using the National Research Council Canada word-emotion association lexicon to assign emotional scores to reviews for different subpopulations according to gender, gender and sanction, and gender and rating. ResultsWe found statistically significant differences in the sentiment and emotion of reviews between male and female physicians. Numerical ratings are lower and sentiment in text reviews is more negative for women who will be sanctioned than for men who will be sanctioned; sanctioned male physicians are still associated with positive reviews. ConclusionsGiven the growing impact of web-based reviews on demand for physician services, understanding the different dynamics of reviews for male and female physicians is important for consumers and platform architects who may revisit their platform design.https://formative.jmir.org/2022/9/e34902 |
| spellingShingle | Julia Barnett Margrét Vilborg Bjarnadóttir David Anderson Chong Chen Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study JMIR Formative Research |
| title | Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study |
| title_full | Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study |
| title_fullStr | Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study |
| title_full_unstemmed | Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study |
| title_short | Understanding Gender Biases and Differences in Web-Based Reviews of Sanctioned Physicians Through a Machine Learning Approach: Mixed Methods Study |
| title_sort | understanding gender biases and differences in web based reviews of sanctioned physicians through a machine learning approach mixed methods study |
| url | https://formative.jmir.org/2022/9/e34902 |
| work_keys_str_mv | AT juliabarnett understandinggenderbiasesanddifferencesinwebbasedreviewsofsanctionedphysiciansthroughamachinelearningapproachmixedmethodsstudy AT margretvilborgbjarnadottir understandinggenderbiasesanddifferencesinwebbasedreviewsofsanctionedphysiciansthroughamachinelearningapproachmixedmethodsstudy AT davidanderson understandinggenderbiasesanddifferencesinwebbasedreviewsofsanctionedphysiciansthroughamachinelearningapproachmixedmethodsstudy AT chongchen understandinggenderbiasesanddifferencesinwebbasedreviewsofsanctionedphysiciansthroughamachinelearningapproachmixedmethodsstudy |