KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Technique for Product Effect Analysis Using Online Customer Reviews

온라인 고객 리뷰를 활용한 제품 효과 분석 기법

  • 임영서 (동덕여자대학교 정보통계학과) ;
  • 이소영 (동덕여자대학교 정보통계학과) ;
  • 이지나 (동덕여자대학교 문헌정보학과) ;
  • 류보경 (동덕여자대학교 정보통계학과) ;
  • 김현희 (동덕여자대학교 정보통계학과)
  • Received : 2020.04.22
  • Accepted : 2020.07.28
  • Published : 2020.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a novel scheme for product effect analysis, termed PEM, to find out the effectiveness of products used for improving the current condition, such as health supplements and cosmetics, by utilizing online customer reviews. The proposed technique preprocesses online customer reviews to remove advertisements automatically, constructs the word dictionary composed of symptoms, effects, increases, and decreases, and measures products' effects from online customer reviews. Using Naver Shopping Review datasets collected through crawling, we evaluated the performance of PEM compared to those of two methods using traditional sentiment dictionary and an RNN model, respectively. Our experimental results shows that the proposed technique outperforms the other two methods. In addition, by applying the proposed technique to the online customer reviews of atopic dermatitis and acne, effective treatments for them were found appeared on online social media. The proposed product effect analysis technique presented in this paper can be applied to various products and social media because it can score the effect of products from reviews of various media including blogs.

본 논문에서는 온라인 고객 리뷰를 활용하여 건강 보조제, 화장품 등 현재의 상태를 개선하기 위해 사용되는 제품을 대상으로 그 효과를 알아보기 위한 제품 효과 분석 기법을 제시하였다. 제안하는 제품 효과 분석 기법은 블로그 포스팅에 존재하는 광고를 자동 제거하고, 효과 분석을 위한 증상, 효과, 증가, 및 감소로 이루어진 단어 사전을 구축하며, 제안하는 알고리즘을 통해 제품의 효과를 측정한다. 제품 효과 분석 기법을 검증하기 위해 정답 레이블이 존재하는 네이버 쇼핑 리뷰 데이터셋을 대상으로 성능평가를 실시하였으며, 전통적인 긍부정 사전과 RNN 모델과 성능을 비교하였다. 실험 결과, 본 논문에서 제안하는 효과 분석 기법이 다른 두가지 방법보다 정확도가 뛰어남을 보여주었다. 또한, 아토피 피부염, 여드름 치료제에 제안하는 기법을 적용하여 소셜 미디어에 나타난 효과적인 치료법을 소개하였다. 본 논문에서 제시한 알고리즘은 블로그를 포함한 여러 매체의 리뷰로부터 제품의 효과를 점수화할 수 있으므로 다양한 제품군과 소셜 미디어에 적용될 수 있을 것으로 보인다.

Keywords

References

  1. B. H. Back and I. K. Ha, “Comparison of Sentiment Analysis from Large Twitter Data Sets by Naive Bayes and Natural Language Processing Methods,” Journal of information and Communication Convergence Engineering, Vol. 17, No. 4, pp. 239-245, 2019. https://doi.org/10.6109/jicce.2019.17.4.239
  2. M, Ryan and S. Y. Han, "Web Scraping with Python," Hanbit Publishing Network, 2019.
  3. C. Deepti, J. Nisheeth, I. Mathur, and Y. J. Yu, "Mastering Natural Language Processing with Python," Acorn Publishing, 2017.
  4. S. M. Park, C. W. Na, M. S. Choi, D. H. Lee, and B. W. On, “KNU Korean Sentiment Lexicon - Bi-LSTM-based Method for Building a Korean Sentiment Lexicon,” Journal of Intelligence and Information Systems, Vol. 24, No. 4, pp. 219-240, 2018. https://doi.org/10.13088/JIIS.2018.24.4.219
  5. P. S. Jang, “Study on Principal Sentiment Analysis of Social Data,” Journal of the Korea Society of Computer and Information, Vol. 19, No. 12, pp. 49-56, 2014. https://doi.org/10.9708/jksci.2014.19.12.049
  6. J. Y. Choi, "A Study on the Text-based Emotion Classification," Inje University Graduate School, pp. 1-41, 2017.
  7. S. C. Choi, "A Study on Development of Korean Basketball League through Big Data Sentiment Analysis," Sookmyung Women's University Graduate School, pp. 1-121, 2018.
  8. J. J. Lee, "Sentiment Analysis based on Korean using Recurrent Neural Network: focused on Online Movie Review," Kookmin University Graduate School Department of Data Science Data Science Major, pp. 1-54, 2018.
  9. W. H. Kim, “Influencer, drug or bad?,” Korea Marketing Association, Vol. 53, No. 11, pp. 9-15, 2019.
  10. Y. S. Lim, S. Y. Lee, J. N. Lee, and B. K. Ryu, "An Analytical Effect Model for Atopic Therapy Using Social Media," In Proceedings of the Korea Information Processing Society, Vol. 28, No. 2, pp. 742-745, 2019.
  11. C. W. Jun, T. Y. Choi, and J. H. Cho, "Natural Language Processing Starts with TensorFlow and Machine Learning," Wikibook, 2019.
  12. D. H. Lee, E. J. Do, J. Y. Lee, Y. Park, J. W. Oh, M. H. Lee, S. J. Hong, S. Y. Lee, J. S. Park, D. H. Nam, and H. Y. Yeom, “Multicenter questionnaires on the current management of atopic dermatitis in Korea,” Allergy Asthma & Respiratory Diseases, Vol. 4, No. 4, pp. 271-275, 2016. https://doi.org/10.4168/aard.2016.4.4.271
  13. M. J. Kim, “Acne Prevention and Treatment Research,” The New Medical Journal, Vol. 42, No. 3, pp. 1-17, 1999.
  14. D. H. Kim, G. H. Gang, G. W. Kim, and I. Y. Yoo, “Management of Children with Atopic Dermatitis,” Allergy Asthma & Respiratory Diseases, Vol. 18, No. 2, pp. 39-48, 2008.