A large-scale quantitative analysis of latent factors and sentiment in online doctor reviews

Wallace, Byron C
Paul, Michael J
Sarkar, Urmimala
Trikalinos, Thomas A
Dredze, Mark

¹Department of Health Services Policy & Practice, Brown University, Providence, Rhode Island, USA
²Department of Computer Science, Johns Hopkins University, Baltimore, Maryland, USA
³Department of Medicine, UCSF, San Francisco, California, USA
⁴Johns Hopkins University, Human Language Technology Center of Excellence, Baltimore, Maryland, USA

Dr Byron C Wallace, Department of Health Services Policy & Practice, Brown University, Providence, RI 02912, USA; [email protected]

Received February 11, 2014

Received in revised form May 14, 2014

Accepted May 27, 2014

JAMIA - Journal of the American Medical Informatics Association 21(6):p 1098-1103, November 2014. | DOI: 10.1136/amiajnl-2014-002711

Online physician reviews are a massive and potentially rich source of information capturing patient sentiment regarding healthcare. We analyze a corpus comprising nearly 60 000 such reviews with a state-of-the-art probabilistic model of text. We describe a probabilistic generative model that captures latent sentiment across aspects of care (eg, interpersonal manner). We target specific aspects by leveraging a small set of manually annotated reviews. We perform regression analysis to assess whether model output improves correlation with state-level measures of healthcare. We report both qualitative and quantitative results. Model output correlates with state-level measures of quality healthcare, including patient likelihood of visiting their primary care physician within 14 days of discharge (p=0.03), and using the proposed model better predicts this outcome (p=0.10). We find similar results for healthcare expenditure. Generative models of text can recover important information from online physician reviews, facilitating large-scale analyses of such reviews.