DOI QR코드

DOI QR Code

Rating Prediction by Evaluation Item through Sentiment Analysis of Restaurant Review

  • So, Jin-Soo (Dept. of Computer Engineering, Daejin University) ;
  • Shin, Pan-Seop (Dept. of Computer Engineering, Daejin University)
  • Received : 2020.03.10
  • Accepted : 2020.05.26
  • Published : 2020.06.30

Abstract

Online reviews we encounter commonly on SNS, although a complex range of assessment information affecting the consumer's preferences are included, it is general that such information is just provided by simple numbers or star ratings. Based on those review types, it is not easy to get specific information that consumers want and use it to make a decision for purchase. Therefore, in this study, we propose a prediction methodology that can provide ratings broken down by evaluation items by performing sentiment analysis on restaurant reviews written in Korean. To this end, we select 'food', 'price', 'service', and 'atmosphere' as the main evaluation items of restaurants, and build a new sentiment dictionary for each evaluation item. It also classifies review sentences by rating item, predicts granular ratings through sentiment analysis, and provides additional information that consumers can use to make decisions. Finally, using MAE and RMSE as evaluation indicators it shows that the rating prediction accuracy of the proposed methodology has been improved than previous studies and presents the use case of proposed methodology.

우리가 SNS상에서 흔하게 접하는 온라인 리뷰에는, 소비자들의 선호도에 영향을 미치는 다양한 평가정보가 복합적으로 포함되어 있지만 이를 매우 간단한 형태의 수치(또는 평점)로 제공하는 것이 일반적이다. 이러한 리뷰에서, 소비자가 원하는 구체적인 정보를 얻고, 이를 구매를 위한 판단에 활용하기란 쉽지 않다. 따라서 본 연구에서는 한국어로 작성된 음식점 리뷰를 대상으로, 감성분석을 수행하여 평가항목별로 세분화된 평점을 제공 가능한 예측 방법론을 제안한다. 이를 위해, 음식점의 주요 평가항목으로 '음식', '가격', '서비스', '분위기'를 선정하고, 평가항목별 맞춤형 감성사전을 새롭게 구축한다. 또한 평가항목별 리뷰 문장을 분류하고 감성분석을 통해 세분화된 평점을 예측하여 소비자가 의사결정에 활용 가능한 추가적인 정보를 제공한다. 마지막으로, MAE와 RMSE를 평가지표로 사용하여 기존의 연구보다 제안기법의 평점 예측 정확도가 향상되었음을 보이며, 제안 방법론의 활용 사례도 제시한다.

Keywords

References

  1. R. A. Peterson, and C. M. Maria, "Consumer Behavior(7th ed)" Upper Saddle River, NJ: Prentice-Hall, Inc. 2003
  2. S. Basuroy, S. Chatterjee, and S. A. Ravid, "How Critical are Critical Reviews? The Box Office Effects of Film Critics, Star-power and Budgets", Journal of Marketing, Vol. 67, No. 4, pp. 103-117, Oct 2003. DOI: 10.1509/jmkg.67.4.103.18692
  3. W. Duan, B. Gu, and A. B. Whinston, "Do online reviews matter?-An empirical investigation of panel data", Decision Support Systems, Vol. 45, No. 4, pp. 1007-1016, Nov 2008. DOI: 10.1016/j.dss.2008.04.001
  4. Jungkook An, and Hee-Woong Kim, "Building a Korean Sentiment Lexicon Using Collective Intelligence", Journal of Intelligence and Information Systems, Vol. 21, No. 2, pp. 49-67, Jun 2015. DOI: 10.13088/jiis.2015.21.2.49
  5. B. Bickart, and R. Schindler, "Internet Forums as Influential Sources of Consumer Information", Journal of Interactive Marketing, Vol. 15, No. 3, pp. 31-40, Jan 2001. DOI: 10.1002/dir.1014
  6. Jongseok Song, and Soowon Lee, "Automatic Construction of Positive/Negative Feature-Predicate Dictionary for Polarity Classification of Product Reviews", The Korean Institute of Information Scientists and Engineers: Software and Application, Vol. 38, No. 3, pp. 157-168, Mar 2011.
  7. Eunji Yu, Yoosin Kim, Namgyu Kom, and Seung Ryul Jeong, "Predicting the Direction of the Stock Index by Using a Domain-Specific Sentiment Dictionary", Journal of Intelligence and Information Systems, Vol. 19, No. 1, pp. 95-110, Mar 2013. DOI: 10.13088/jiis.2013.19.1.095
  8. Sang Hoon Lee, Jing Cui, and Jong Woo Kim, "Sentiment analysis on movie review through building modified sentiment dictionary by movie genre", Journal of Intelligence and Information Systems, Vol. 22, No. 2, pp. 97-113, Jun 2016. DOI: 10.13088/jiis.2016.22.2.097
  9. Woo-Young Jeong, Byung-Chull Bae, Sung Hyun Cho, and Shin-Jin Kang, "Construction and Evaluation of a Sentiment Dictionary Using a Web Corpus Collected from Game Domain", Journal of Korea Game Society, Vol. 18, No. 5, pp. 113-121, Oct 2018. DOI: 10.7583/JKGS.2018.18.5.113
  10. B. Pang, and L. Lee, "A Sentiment Education : Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts", Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL-04), pp. 271-278, Jul 2004. DOI: 10.3115/1218955.1218990
  11. R. Moraes, J. Francisco, and W. Neto, "Document-level sentiment classification: An empirical comparison between SVM and ANN", Expert Systems with Applications, Vol. 40, No. 2, pp. 621-633, Feb 2013. DOI: 10.1016/j.eswa.2012.07.059
  12. Misun Kim, Hyungjeong Yang, Tien Nguyen Anh, Jongmin Joo, and Chaeho Jin, "Sentiment Analysis of Movie Review Using Integrated CNN-LSTM Model", KIISE Trans. on Computing Practices, Vol. 24, No. 11, pp. 623-627, Nov 2018. DOI: 10.5626/ktcp.2018.24.11.623
  13. Ho-yeon Park, and Kyoung-jae Kim, "Sentiment Analysis of Movie Review Using Integrated CNN-LSTM Model", Journal of Intelligence and Information Systems, Vol. 25, No. 4, pp. 141-154, Dec 2019. DOI: 10.13088/jiis.2019.25.4.141
  14. Jiyeon Hyun, Sangyi Ryu, and Sang-Yong Tom Lee, "How to improve the accuracy of recommendation systems: Combining ratings and review texts sentiment scores", Journal of Intelligence and Information Systems, Vol. 25, No. 1, pp. 219-239, Mar 2019. DOI: 10.13088/jiis.2019.25.1.219
  15. Hyun Woong Cho, Woo Je Kim, and Man Sik Kim, "The model for review rating prediction using review data", Proceeding of The Korea Society of IT Services Autumn Conference, pp. 471-474, 2015.
  16. Sang-Hyun Park, Hyun-Sil Moon, and Jae-Kyung Kim, "Overall prediction of online review using Topic modeling and Neural network", Korea Intelligent Information Systems Society, pp. 56-56, Nov 2016.
  17. KyongMin Kim, MuHyok Ahn, YounHo Lee, "Detection of Malicious Rate Evaluation and Prediction of True Rate in Movie Rating", Journal of the Korean Institute of Information Scientists and Engineers: Computing Practices and Letters, Vol. 20, No. 4, pp. 213-218, April 2014.
  18. TripAdvisor, http://www.tripadvisor.co.kr/
  19. Sang-Min Park, Chul-Won Na, Min-Seong Choi, Da-Hee Lee, and Byung-Won 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, Dec 2018. DOI: 10.13088/jiis.2018.24.4.219
  20. N. Lalithamani, L. S. Thati, and R. Adhikesavan, "Sentence-level Semtiment Polarity Calculation for Customer Reviews by Considering Complex Sentential Structures", IJRET: International Journal of Research in Engineering and Technology, Vol. 3, No. 3, pp. 433-438, Mar 2014. DOI: 10.15623/ijret.2014.0303081