Detecting salient aspects in online reviews of health providers.

We present a fully automated method to capture what topics health consumers discuss when reviewing their health providers online. Our method does not rely on any manual tagging of the information, and operates on the text of online reviews. We analyze a large set of reviews and compare the topics discussed when reviewing providers with different specialties. This work provides a complementary view on the traditional qualitative approaches proposed so far to capturing factors for patient satisfaction. Furthermore, our research contributes to understanding in a bottom-up fashion the needs and interests of health consumers online.

[1]  W H Rogers,et al.  Patients' ratings of outpatient visits in different practice settings. Results from the Medical Outcomes Study. , 1993, JAMA.

[2]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[3]  W. Chou,et al.  Social Media Use in the United States: Implications for Health Communication , 2009, Journal of medical Internet research.

[4]  J. Wareham,et al.  Health 2.0 and Medicine 2.0: Tensions and Controversies in the Field , 2008, Journal of medical Internet research.

[5]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[6]  Sean M. O'Brien,et al.  Identifying high-quality hospitals: consult the ratings or flip a coin? , 2007, Archives of internal medicine.

[7]  Ivan Titov,et al.  A Joint Model of Text and Aspect Ratings for Sentiment Summarization , 2008, ACL.

[8]  Dong-Hong Ji,et al.  I2R: Three Systems for Word Sense Discrimination, Chinese Word Sense Disambiguation, and English Word Sense Disambiguation , 2007, SemEval@ACL.

[9]  Lise Getoor,et al.  A Latent Dirichlet Model for Unsupervised Entity Resolution , 2005, SDM.

[10]  Eytan Domany,et al.  Resampling Method for Unsupervised Estimation of Cluster Validity , 2001, Neural Computation.

[11]  G. Eysenbach.  Medicine 2.0: Social Networking, Collaboration, Participation, Apomediation, and Openness , 2008, Journal of medical Internet research.

[12]  W. Bruce Croft,et al.  LDA-based document models for ad-hoc retrieval , 2006, SIGIR.

[13]  Gunther Eysenbach,et al.  From Intermediation to Disintermediation and Apomediation: New Models for Consumers to Access and Assess the Credibility of Health Information in the Age of Web2.0 , 2007, MedInfo.

[14]  L. Frostholm,et al.  The Uncertain Consultation and Patient Satisfaction: The Impact of Patients' Illness Perceptions and a Randomized Controlled Trial on the Training of Physicians' Communication Skills , 2005, Psychosomatic medicine.

[15]  Lillian Lee,et al.  Opinion Mining and Sentiment Analysis , 2008, Found. Trends Inf. Retr..

[16]  Noémie Elhadad,et al.  An Unsupervised Aspect-Sentiment Model for Online Reviews , 2010, NAACL.