Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Research on Constructing a Sentiment Lexicon for the F&B Sector based on the N-gram Framework

  • Yeryung Moon (School of ICT & GE, Handong Global University) ;
  • Gaeun Son (School of ICT & GE, Handong Global University) ;
  • Geonuk Nam (School of ICT & GE, Handong Global University) ;
  • Hanjin Lee (School of Creative Convergence Education, Handong Global University)
  • Received : 2024.07.31
  • Accepted : 2024.09.25
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Online and mobile reviews strongly influence consumer behavior, especially in the service industry, and play a key role in determining customer retention and revisit rates. Systematically analyzing the information in these reviews can effectively assess how they directly influence customers' purchase decisions. In this study, we applied the existing KNU sentiment dictionary to food and beverage (F&B) review data to build a customized sentiment lexicon using N-grams based on about 10,000 reviews. Comparing its performance with the existing dictionary, we found that the sentiment lexicon generated using the 1-gram, 2-gram, and 3-gram models had the highest accuracy, precision, recall, and F1 scores. These results can serve as a powerful business support tool for SMEs in the F&B and grocery shopping sector, also be used to predict customer demand for technology and policy.

구매경험 후기는 온라인 및 모바일 서비스 산업에서 소비자 행동에 큰 영향을 미치며, 지속적인 이용여부를 결정짓는 중요한 요소이다. 이에 리뷰에서 제공되는 정보를 체계적으로 분석하면 고객의 구매결정에 어떻게 직접적으로 영향을 미치는지 효과적으로 평가할 수 있다. 본 연구에서는 국립국어원 기구축 KNU 감성사전을 식음료(F&B) 분야에 적용하여, N-그램 프레임워크 기반 약 10,000개의 리뷰 데이터 훈련 모델로 검증한 산업특화 감성사전을 구축하였다. 기존 사전과 성능을 비교한 결과, 1-그램, 2-그램, 3-그램 조합 기반 신규 생성된 감성사전이 가장 높은 정확도, 정밀도, 재현율, F1 점수를 나타냈다. 이 분석결과는 F&B 및 식품 부문 소상공인 관점에서 효과적인 비즈니스 지원 도구로도 활용할 수 있으며, 고객 수요예측에도 기술적, 정책적으로 활용할 수 있다.

Keywords

References

  1. H-J. Eom, and H-J. Jin. (2024). "Analysis of the Effect of Online Reviews on Restaurant Rankings," Korean Journal of Hospitality & Tourism, 33(1), 57-77. https://doi.org/10.24992/KJHT.2024.2.33.01.57
  2. J.Y. Choi, H.A Kim, and Y.B. Kim. (2020). "The Impact of Online Review Volume, Rating, and Sentiment Score on Sales: Focusing on the Moderating Effect of Brand Reputation," Journal of Channel and Retailing, 25(3), 1-21. https://doi.org/10.17657/jcr.2020.07.31.1
  3. J-P. Park, and H. Chun. (2022). "Effects of Electronic Word-of-Mouth Quality on Information Satisfaction and Purchase Intention among Consumer Reviews on Food Delivery Apps," Journal of Tourism and Leisure Research, 34(5), 347-364. https://doi.org/10.31336/jtlr.2022.5.34.5.347
  4. P. Mehta, and S. Pandya. (2020). "A review on sentiment analysis methodologies, practices and applications," International Journal of Scientific and Technology Research, 9(2), 601-609.
  5. H.-M. Kim, and K. Park. (2019). "Sentiment analysis of online food product review using ensemble technique," Journal of Digital Convergence, 17(4), 115-122. https://doi.org/10.14400/JDC.2019.17.4.115
  6. J. Kim, W. Hou, and H. Kahn. (2020). "The Power of Online Review: Consumer Evaluation Based on Online Review Types," Journal of Product Research, 38(4), 21-30. https://doi.org/10.36345/kacst.2020.38.4.004
  7. J-S. So, and P-S. Shin. (2020). "Rating Prediction by Evaluation Item through Sentiment Analysis of Restaurant Review," Journal of the Korea Society of Computer and Information, 25(6), 81-89. https://doi.org/10.9708/jksci.2020.25.06.081
  8. S.-H. Park, Y.-E. Lee, and H.-J. Lee, "Research on Enhancing Customer Experience through AI-Supported Review Generation," The transactions of The Korean Institute of Electrical Engineers, 73(2), 334-342. https://doi.org/10.5370/kiee.2024.73.2.334
  9. H. H. Gil. (2018). "A study on Korean unused word list for text mining," The Korean Language and Literature, 78, 1-25. https://doi.org/10.18628/urimal.78.201809.1
  10. M. K. Cho, and B. J. Lee. (2021). "Comparison of service quality of full service carriers in Korea using topic modeling: based on reviews from TripAdvisor," Journal of Hospitality and Tourism Studies, 23(1), 152-165, https://doi.org/10.31667/jhts.2021.2.86.152
  11. BL. Chua, S. Karim, S. Lee, and H. Han. (2020). "Customer Restaurant Choice: An Empirical Analysis of Restaurant Types and Eating-out Occasions," Int'l Journal of Environmental Research and Public Health, 17(17), 6276. https://doi.org/10.3390/ijerph17176276
  12. S. Li, S. Yun, and Y.W. Woo. (2019). "Crawling Methods for Web Data of Various Formats using Python," Proceedings of General Conference of the Korean Institute of Information and Communication Sciences, 343-346.
  13. J-H. Jung, H-I. Chung, and Z-K. Lee. (2021). "An Analysis of Mobile Food Delivery App Baemin by Using Text Mining and ARIMA Model," Journal of Digital Contents Society, 22(2), 291-299, https://doi.org/10.9728/dcs.2021.22.2.291
  14. S.-W. Kang, and W.-G. Seo. (2023, October 26). "Generate a Domain-specific Sentiment Lexicon for Stock Price Prediction," Proceedings of the General Conference of the Korean Institute of Information and Communication Sciences, Gyeonggi.
  15. J. Kim, D. Lee, E. Lee, Y. Park, Y. Shin, and O. Kwon. (2023, May 31). "Development of a Sophisticated Sentiment Lexicon for an Automated Food Safety Inspection System," Proceedings of the Spring Joint Conference of the Korean Institute of Industrial Engineers, Jeju.
  16. H. Kang, and H. Song. (2021). "Constructing Sentiment Lexicon for Subject-Specific Sentiment Analysis," Korean Linguistics, 93, 83-110, https://doi.org/10.20405/kl.2021.11.93.83
  17. Z. Mengjuan, H. Changping, and S. Yu. (2022). "Sentiment Lexicon Construction for Chinese Book Reviews Based on Ultrashort Reviews," The Electronic Library, 40(3), 221-236. https://doi.org/10.1108/EL-07-2021-0147
  18. A. Dey, M. Jenamani, and J.J. Thakkar. (2018). "Senti-N-Gram: An n-Gram Lexicon for Sentiment Analysis," Expert Systems with Applications, 103, 92-105. https://doi.org/10.1016/jeswa.2018.03.004.
  19. F. Yin, Y. Wang, J. Liu, and L. Lin. (2020). "The Construction of Sentiment Lexicon Based on Context-Dependent Part-of-Speech Chunks for Semantic Disambiguation," IEEE Access, 8, 63359-63367.
  20. A. B. Cantor. (1996). "Sample-size Calculations for Cohen's Kappa," Psychological Methods, 1(2), 150-153. https://doi.org/10.1037/1082-989X.1.2.15
  21. M. Lerasle. (2012). "Optimal Model Selection in Density Estimation," Annales de l'I.H.P. Probabilites et Statistiques, 48(3), 884-908. https://doi.org/10.1214/11-AIHP425.
  22. E. Melilli, and P. Veronese. (2024). "Confidence Distributions and Hypothesis Testing," Stat. Papers, 65, 3789-3820. https://doi.org/10.1007/s00362-024-01542-4
  23. S-W. Kim, and J-M. Song. (2021). "Statistical Hypothesis Testing using Deep Learning: Focusing on Two Sample T-Test," Journal of the Korean Data And Information Science Society, 32(1), 25-35. https://doi.org/10.7465/jkdi.2021.32.1.25