Use of Sentiment Mining and Online NMF for Topic Modeling Through the Analysis of Patients Online Unstructured Comments

  • Adnan Muhammad ShahEmail author
  • Xiangbin Yan
  • Syed Jamal Shah
  • Salim Khan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10983)


Patients have posted thousands of online reviews to assess their doctors’ performance. Mechanisms to collect unstructured feedback from patients of healthcare providers have become very common, but there are scarce researches on different analysis techniques to examine such feedback have not frequently been applied in this context. We apply text mining techniques to compare online physician reviews from RateMDs and Healthgrades, to measure the systematic similarities and differences in patient reviews between these two platforms. We use sentiment analysis techniques to categorize online patients’ reviews as either positive or negative descriptions of their health care. We apply a customized text mining technique, ONMF topic modeling to identify the major topics on two platforms. Our text mining techniques revealed research area on how to use big data and text mining techniques to help health care providers, and organizations hear patient voices to improve the health service quality.


Text mining Sentiment analysis Topic modeling Physician reviews 



This research is supported by the National Natural Science Foundation, People’s Republic of China (No.71531013, 71401047, 71729001).


  1. 1.
    Greaves, F., et al.: Associations between internet-based patient ratings and conventional surveys of patient experience in the English NHS: an observational study. BMJ Qual. Saf. 21, 600 (2012)CrossRefGoogle Scholar
  2. 2.
    Hao, H., Zhang, K.: The voice of chinese health consumers: a text mining approach to web-based physician reviews. J. Med. Internet Res. 18, e108 (2016)CrossRefGoogle Scholar
  3. 3.
    Hao, H., Zhang, K., Wang, W., Gao, G.: A tale of two countries: International comparison of online doctor reviews between China and the United States. Int. J. Med. Inform. 99, 37–44 (2017)CrossRefGoogle Scholar
  4. 4.
    Wallace, B.C., Paul, M.J., Sarkar, U., Trikalinos, T.A., Dredze, M.: A large-scale quantitative analysis of latent factors and sentiment in online doctor reviews. J. Am. Med. Inform. Assoc. 21, 1098–1103 (2014)CrossRefGoogle Scholar
  5. 5.
    Kadry, B., Chu, F.L., Kadry, B., Gammas, D., Macario, A.: Analysis of 4999 online physician ratings indicates that most patients give physicians a favorable rating. J. Med. Internet Res. 13, e95 (2011)CrossRefGoogle Scholar
  6. 6.
    Emmert, M., Meier, F., Pisch, F., Sander, U.: Physician choice making and characteristics associated with using physician-rating websites: cross-sectional study. J. Med. Internet Res. 15, e187 (2013)CrossRefGoogle Scholar
  7. 7.
    Xiang, Z., Du, Q., Ma, Y., Fan, W.: A comparative analysis of major online review platforms: Implications for social media analytics in hospitality and tourism. Tour. Manag. 58, 51–65 (2017)CrossRefGoogle Scholar
  8. 8.
    Liu, Y., Bi, J.-W., Fan, Z.-P.: Ranking products through online reviews: a method based on sentiment analysis technique and intuitionistic fuzzy set theory. Inf. Fusion 36, 149–161 (2017)CrossRefGoogle Scholar
  9. 9.
    Giatsoglou, M., Vozalis, M.G., Diamantaras, K., Vakali, A., Sarigiannidis, G., Chatzisavvas, K.C.: Sentiment analysis leveraging emotions and word embeddings. Expert Syst. Appl. 69, 214–224 (2017)CrossRefGoogle Scholar
  10. 10.
    Alemi, F., Torii, M., Clementz, L., Aron, D.C.: Feasibility of real-time satisfaction surveys through automated analysis of patientsʼ unstructured comments and sentiments. Qual. Manag. Health Care 21, 9–19 (2012)CrossRefGoogle Scholar
  11. 11.
    Greaves, F., Ramirez-Cano, D., Millett, C., Darzi, A., Donaldson, L.: Use of sentiment analysis for capturing patient experience from free-text comments posted online. J. Med. Internet Res. 15, e239 (2013)CrossRefGoogle Scholar
  12. 12.
    Tu, D., Chen, L., Lv, M., Shi, H., Chen, G.: Hierarchical online NMF for detecting and tracking topic hierarchies in a text stream. Pattern Recogn. 76, 203–214 (2018)CrossRefGoogle Scholar
  13. 13.
    Klein, C., Clutton, P., Polito, V.: Topic modeling reveals distinct interests within an online conspiracy forum. Front. Psychol. 9, 189 (2018)CrossRefGoogle Scholar
  14. 14.
    Gao, G.G., McCullough, S.J., Agarwal, R., Jha, K.A.: A changing landscape of physician quality reporting: analysis of patients? Online ratings of their physicians over a 5-year period. J. Med. Internet Res. 14, e38 (2012)CrossRefGoogle Scholar
  15. 15.
    Jack, R.A., Burn, M.B., McCulloch, P.C., Liberman, S.R., Varner, K.E., Harris, J.D.: Does experience matter? A meta-analysis of physician rating websites of orthopaedic surgeons. Musculoskelet. Surg. 102, 63–71 (2018)Google Scholar
  16. 16.
    Alemi, F., Torii, M., Clementz, L., Aron, D.C.: Feasibility of real-time satisfaction surveys through automated analysis of patients’ unstructured comments and sentiments. Qual. Manag. Health Care 21, 9–19 (2012)CrossRefGoogle Scholar
  17. 17.
    Guo, Y., Barnes, S.J., Jia, Q.: Mining meaning from online ratings and reviews: tourist satisfaction analysis using latent dirichlet allocation. Tourism Manag. 59, 467–483 (2017)CrossRefGoogle Scholar
  18. 18.
    García-Pablos, A., Cuadros, M., Rigau, G.: W2VLDA: almost unsupervised system for aspect based sentiment analysis. Expert Syst. Appl. 91, 127–137 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Adnan Muhammad Shah
    • 1
    Email author
  • Xiangbin Yan
    • 1
  • Syed Jamal Shah
    • 1
  • Salim Khan
    • 1
  1. 1.School of ManagementHarbin Institute of TechnologyHarbinPeople’s Republic of China

Personalised recommendations