Reviews Analysis of Korean Clinics Using LDA Topic Modeling

Cho-Myong Kim; A-Ram Jo; Yang-Kyun Kim; Kim, Cho-Myong; Jo, A-Ram; Kim, Yang-Kyun

doi:10.13048/jkm.22007

JKM > Volume 43(1); 2022 > Article

Kim, Jo, and Kim: Reviews Analysis of Korean Clinics Using LDA Topic Modeling

Original Article

The Journal of Korean Medicine 2022; 43(1): 73-86.

Published online: March 1, 2022

DOI: https://doi.org/10.13048/jkm.22007

Reviews Analysis of Korean Clinics Using LDA Topic Modeling

Cho-Myong Kim¹

, A-Ram Jo

, Yang-Kyun Kim¹^{, *}

¹Department of Healthcare management, Graduate School, Kyung Hee University

Correspondence to: Yang-Kyun Kim, Department of Healthcare management, Graduate School, Kyung Hee University, 26, Kyungheedae-ro, Dongdaemun-gu, Seoul, 02447, Republic of Korea, Tel: +82-2-961-0748, E-mail: lukekim@khu.ac.kr

Received February 11, 2022 Revised February 21, 2022 Accepted February 22, 2022

Abstract

Objectives

In the health care industry, the influence of online reviews is growing. As medical services are provided mainly by providers, those services have been managed by hospitals and clinics. However, direct promotions of medical services by providers are legally forbidden. Due to this reason, consumers, like patients and clients, search a lot of reviews on the Internet to get any information about hospitals, treatments, prices, etc. It can be determined that online reviews indicate the quality of hospitals, and that analysis should be done for sustainable hospital marketing.

Method

Using a Python-based crawler, we collected reviews, written by real patients, who had experienced Korean medicine, about more than 14,000 reviews. To extract the most representative words, reviews were divided by positive and negative; after that reviews were pre-processed to get only nouns and adjectives to get TF(Term Frequency), DF(Document Frequency), and TF-IDF(Term Frequency – Inverse Document Frequency). Finally, to get some topics about reviews, aggregations of extracted words were analyzed by using LDA(Latent Dirichlet Allocation) methods. To avoid overlap, the number of topics is set by Davis visualization.

Results and Conclusions

6 and 3 topics extracted in each positive/negative review, analyzed by LDA Topic Model. The main factors, consisting of topics were 1) Response to patients and customers. 2) Customized treatment (consultation) and management. 3) Hospital/Clinic’s environments.

Keywords: Reviews analysis, Health Services Management, Clinics of Korean medicine, Latent Dirichlet Allocation, Topic modeling

Fig. 1

Distribution and Most Relevant Terms for positive Topic 1 (Topic number (ex.Topic ‘5’) are ignored)

Fig. 2

Distribution and Most Relevant Terms for positive Topic 2 (Topic number (ex.Topic ‘6’) are ignored)

Fig. 3

Distribution and Most Relevant Terms for positive Topic 3 (Topic number (ex.Topic ‘1’) are ignored)

Fig. 4

Distribution and Most Relevant Terms for positive Topic 4 (Topic number (ex.Topic ‘2’) are ignored)

Fig. 5

Distribution and Most Relevant Terms for positive Topic 5 (Topic number (ex.Topic ‘3’) are ignored)

Fig. 6

Distribution and Most Relevant Terms for positive Topic 6 (Topic number (ex.Topic ‘4’) are ignored)

Fig. 7

Distribution and Most Relevant Terms for positive Topic 1 (Topic number (ex.Topic ‘3’) are ignored)

Fig. 8

Distribution and Most Relevant Terms for positive Topic 2 (Topic number (ex.Topic ‘3’) are ignored)

Fig. 9

Distribution and Most Relevant Terms for positive Topic 3 (Topic number (ex.Topic ‘2’) are ignored)

Table 1

The number of hospitals and positive/negative reviews by region

지역	서울	경기	인천	대구	대전	광주	울산	경남	전북
병원수	1369	978	246	256	164	164	199	132	95
긍정리뷰 수	5644	3482	973	669	595	496	484	408	347
부정리뷰 수	244	114	27	15	16	10	16	10	11

지역	경북	부산	충남	충북	강원	전남	세종	제주

병원수	93	82	76	75	61	61	22	6
긍정리뷰 수	271	259	255	206	193	141	72	10
부정리뷰수	10	6	9	5	3	7	1	0

Table 2

Positive review topics and extracted representative keywords by using LDA model

	word 1	word 2	word 3	word 4	word 5	word 6	word 7	word 8	word 9	word 10	word 11	word 12	word 13	word 14	word 16
Topic 1	보약	전문	한결	손님	양방	산후	손가락	오다	엄마	골반	어머니	대화	염좌	강추	위주
Topic 2	감기	흉터	결제	기구	상가	기운	피로	질병	멀리	기대	안정	면역	생기	아파트	요새
Topic 3	치료	진료	병원	선생님	방문	원장	한의원	설명	직원	의사	효과	추천	물리치료	정말	의원
Topic 4	치료	방문	진료	허리	선생님	통증	물리치료	병원	어깨	원장	설명	추나	의사	한의원	직원
Topic 5	체질	한약	다이어트	검사	진맥	확인	처방	상담	복용	곳도	중간	효과	음식	방문	통계
Topic 6	입원	리뷰	오픈	컨디션	무척	인대	처리	나니	염증	교통사고	이름	수술	개원	보험	나은

Table 3

Negative review topics and extracted representative keywords by using LDA model

	Word 1	word 2	word 3	word 4	word 5	word 6	word 7	word 8	word 9	word 10	word 11	word 12	word 13	word 14	word 16
Topic 1	치료	진료	병원	방문	물리치료	의사	효과	선생님	한의원	원장	허리	간호사	통증	의원	설명
Topic 2	지인	체질	진단	상담	한약	추천	후기	보험	건강	소개	한의원	확인	주차	초진	보통
Topic 3	진료	환자	보고	다이어트	설명	직원	효과	상담	병원	처방	원장	검사	선생님	대기	느낌

참고문헌

1. Choi JE, Kim SD, Kim HW. 2018; A Study on Sentiment Score of Healthcare Service Quality on the Hospital Rating. Information Systems Review. 20:2. 111–137. http://dx.doi.org/10.14329/isr.2018.20.2.111

2. Verhoef LM, Van de Belt TH, Engelen LJ, Schoonhoven L, Kool RB. 2014; Social media and rating sites as tools to understanding quality of care: a scoping review. Journal of medical Internet research. 16:2. http://dx.doi.org/10.2196/jmir.3024

3. Lee SH, Jo AR, Lee HY. 2017; The Medical Service Customer’s Satisfaction Factors Extracted from Online Hospital Review Data Using Latent Dirichlet Allocation Method. Journal of Korea Service Management Society. 18:5. 23–44.

4. Choi JE, Kim SD, Kim HW. 2018; A Study on Sentiment Score of Healthcare Service Quality on the Hospital Rating. Information Systems Review. 20:2. 111–137. http://dx.doi.org/10.14329/isr.2018.20.2.111

5. Seo YJ, Kang SH, Kim YH, Choi DB, Shin HK. 2010; Customers’ Utilization and Satisfaction in Oriental Medical Clinics. Journal of Korean Medicine. 31:2. 124–136.

6. Cho CH. 2010; An Effect of Medical Service Quality on Relationship Quality, Customer Satisfaction and Reuse Intent in Oriental Medical Hospital. Korean Journal of Hospital Management. 5:2. 107–132.

7. Han HK, Oh CS, Ryu JS, Im BM. 2014; Comparison of Patients’ Satisfactions with General Korean Medicine Clinics and Networked Korean Medicine Clinics in Seoul, Korea. Journal of Society of Preventive Korean Medicine. 18:3. 57–67.

8. Sparks BA, Browning V. 2012; The impact of online reviews on hotel booking intentions and perception of trust. Tourism management. 32:6. 1310–1323. https://doi.org/10.1016/j.tourman.2010.12.011

9. Sotiriadis MD, Van Zyl C. 2013; Electronic word-of-mouth and online reviews in tourism services: the use of twitter by tourists. Electronic Commerce Research. 13:1. 103–124. https://doi.org/10.1007/s10660-013-9108-1

10. Bickart B, Schindler RM. 2001; Internet forums as influential sources of consumer information. Journal of interactive marketing. 15:3. 31–40. https://doi.org/10.1002/dir.1014

11. Bailey AA. 2005; Consumer awareness and use of product review websites. Journal of Interactive Advertising. 6:1. 68–81. https://doi.org/10.1080/15252019.2005.10722109

12. Kim YJ, Hollingshead AB. 2015; Online social influence: Past, present, and future. Annals of the International Communication Association. 39:1. 163–192. https://doi.org/10.1080/23808985.2015.11679175

13. Maslowska E, Malthouse EC, Bernritter SF. 2017; Too good to be true: the role of online reviews’ features in probability to buy. International Journal of Advertising. 36:1. 142–163. https://doi.org/10.1080/02650487.2016.1195622

14. Choi H. 2010; Study on the Effects of Word-of-Mouth’s Marketing Factors and Medical-Care Service Purchase. Korean Journal of Hospital Management. 15:4. 143–164.

15. Lee SH, Jo AR, Lee HY. 2017; The Medical Service Customer’s Satisfaction Factors Extracted from Online Hospital Review Data Using Latent Dirichlet Allocation Method. Journal of Korea Service Management Society. 18:5. 23–44.

16. Ranard BL, Werner RM, Antanavicius T, Schwartz HA, Smith RJ, Meisel ZF, Asch DA, Ungar LH, Merchant RM. 2016; Yelp Reviews Of Hospital Care Can Supplement And Inform Traditional Surveys Of The Patient Experience Of Care. Health affairs (Project Hope). 35:4. 697–705. https://doi.org/10.1377/hlthaff.2015.1030

17. Levy SE, Duan W, Boo S. 2013; An Analysis of One-Star Online Reviews and Responses in the Washington, D.C., Lodging Market. Cornell Hospitality Quarterly. 54:1. 49–63. https://doi.org/10.1177/1938965512464513

18. Raza A, Dehury R. 2021; Dissatisfaction Factors That Influence Customers To Give Low Online Rating To Hospitals. Asia Pacific Journal of Health Management. 16:3. 193–201. https://doi.org/10.24083/apjhm.v16i3.295

19. Lee DW, Kim YS, Shin EJ. 2021; Active Senior Contents Trend Analysis using LDA Topic Modeling. Journal of Internet Computing and Services. 22:5. 35–45. https://doi.org/10.7472/jksii.2021.22.5.35