지능정보연구 (Journal of Intelligence and Information Systems)

  • 제29권4호
  • /
  • Pages.31-49
  • /
  • 2023
  • /
  • 2288-4866(pISSN)
  • /
  • 2288-4882(eISSN)
한국지능정보시스템학회 (Korea Intelligent Information System Society)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 기반 온라인 리뷰를 활용한 추천 모델 개발: 레스토랑 산업을 중심으로

Developing a deep learning-based recommendation model using online reviews for predicting consumer preferences: Evidence from the restaurant industry

  • 김동언 (경희대학교 대학원 빅데이터응용학과) ;
  • 장동수 (경희대학교 대학원 빅데이터응용학과) ;
  • 엄금철 (가천대학교 경영대학 경영학과) ;
  • 이가은 (광운대학교 경영대학 국제통상학부)
  • Dongeon Kim (Department of Big Data Analytics, Graduate School, Kyung Hee University) ;
  • Dongsoo Jang (Department of Big Data Analytics, Graduate School, Kyung Hee University) ;
  • Jinzhe Yan (College of Business, Gachon University) ;
  • Jiaen Li (College of Business, Kwangwoon University)
  • 투고 : 2023.09.14
  • 심사 : 2023.11.17
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

레스토랑 산업의 성장과 함께 레스토랑 오프라인 매장 수는 점차 증가하지만, 소비자는 자신의 선호도에 적합한 레스토랑을 선택하는 데 어려움을 경험하고 있다. 따라서 소비자의 선호도에 맞는 레스토랑을 추천하는 개인화된 추천 서비스의 필요성이 대두하고 있다. 기존 연구에서는 설문조사 및 평점 정보를 활용하여 소비자 선호도를 조사했으나, 이는 소비자의 구체적인 선호도를 효과적으로 반영하는데 어려움이 존재한다. 이러한 배경하에 온라인 리뷰는 방문 동기, 음식 평가 등 레스토랑에 대한 소비자 구체적인 선호도를 효과적으로 반영하기 때문에 필수적인 정보이다. 한편, 일부 연구에서는 리뷰 텍스트에 전통적인 기계학습 기법을 적용하여 소비자의 선호도를 측정하였다. 그러나 이러한 접근 방식은 주변 단어나 맥락을 고려하지 못하는 한계점이 존재한다. 따라서 본 연구는 딥러닝을 효과적으로 활용하여 온라인 리뷰에서 소비자의 선호도를 정교하게 추출하는 리뷰 텍스트 기반 레스토랑 추천 모델을 제안한다. 본 연구에서 제안된 모델은 추출된 높은 수준의 의미론적 표현과 소비자-레스토랑 상호작용을 연결하여 소비자의 선호도를 정확하고 효과적으로 예측한다. 실험 결과에 따르면 본 연구에서 제안된 추천 모델은 기존 연구에서 제안된 여러 모델에 비해 우수한 추천 성능을 보이는 것으로 나타났다.

With the growth of the food-catering industry, consumer preferences and the number of dine-in restaurants are gradually increasing. Thus, personalized recommendation services are required to select a restaurant suitable for consumer preferences. Previous studies have used questionnaires and star-rating approaches, which do not effectively depict consumer preferences. Online reviews are the most essential sources of information in this regard. However, previous studies have aggregated online reviews into long documents, and traditional machine-learning methods have been applied to these to extract semantic representations; however, such approaches fail to consider the surrounding word or context. Therefore, this study proposes a novel review textual-based restaurant recommendation model (RT-RRM) that uses deep learning to effectively extract consumer preferences from online reviews. The proposed model concatenates consumer-restaurant interactions with the extracted high-level semantic representations and predicts consumer preferences accurately and effectively. Experiments on real-world datasets show that the proposed model exhibits excellent recommendation performance compared with several baseline models.

키워드

참고문헌

  1. Abdi, A., Shamsuddin, S. M., Hasan, S., & Piran, J. (2019). Deep learning-based sentiment classification of evaluative text based on Multi-feature fusion. Information Processing & Management, 56(4), 1245-1259. https://doi.org/10.1016/j.ipm.2019.02.018
  2. Al-Shamri, M. Y. H. (2016). User profiling approaches for demographic recommender systems. Knowledge-based systems, 100, 175-187. https://doi.org/10.1016/j.knosys.2016.03.006
  3. Asani, E., Vahdat-Nejad, H., & Sadri, J. (2021). Restaurant recommender system based on sentiment analysis. Machine Learning with Applications, 6, 100114.
  4. Bobadilla, J., Ortega, F., Hernando, A., & Gutierrez, A. (2013). Recommender systems survey. Knowledge-based systems, 46, 109-132. https://doi.org/10.1016/j.knosys.2013.03.012
  5. Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?-Arguments against avoiding RMSE in the literature. Geoscientific model development, 7(3), 1247-1250. https://doi.org/10.5194/gmd-7-1247-2014
  6. Chen, H., Li, Z., & Hu, W. (2016). An improved collaborative recommendation algorithm based on optimized user similarity. The Journal of Supercomputing, 72, 2565-2578. https://doi.org/10.1007/s11227-015-1518-5
  7. Chen, S., & Peng, Y. (2018). Matrix factorization for recommendation with explicit and implicit feedback. Knowledge-based systems, 158, 109-117. https://doi.org/10.1016/j.knosys.2018.05.040
  8. Chhipa, S., Berwal, V., Hirapure, T., & Banerjee, S. (2022). Recipe Recommendation System Using TF-IDF. ITM Web of Conferences,
  9. Das, A. S., Datar, M., Garg, A., & Rajaram, S. (2007). Google news personalization: scalable online collaborative filtering. Proceedings of the 16th international conference on World Wide Web,
  10. Esmaeili, L., Mardani, S., Golpayegani, S. A. H., & Madar, Z. Z. (2020). A novel tourism recommender system in the context of social commerce. Expert Systems with Applications, 149, 113301.
  11. Gao, M., Wu, Z., & Jiang, F. (2011). Userrank for item-based collaborative filtering recommendation. Information Processing Letters, 111(9), 440-446. https://doi.org/10.1016/j.ipl.2011.02.003
  12. Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249-256.
  13. Goldberg, D., Nichols, D., Oki, B. M., & Terry, D. (1992). Using collaborative filtering to weave an information tapestry. Communications of the ACM, 35(12), 61-70. https://doi.org/10.1145/138859.138867
  14. Hassan, A., & Mahmood, A. (2018). Convolutional recurrent deep learning model for sentence classification. IEEE Access, 6, 13949-13957. https://doi.org/10.1109/ACCESS.2018.2814818
  15. Hazrati, N., & Ricci, F. (2022). Recommender systems effect on the evolution of users' choices distribution. Information Processing & Management, 59(1), 102766.
  16. He, X., & Chua, T. S. (2017). Neural factorization machines for sparse predictive analytics. In Proceedings of the 40th International ACM SIGIR conference on Research and Development in Information Retrieval, 355-364.
  17. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., & Chua, T. S. (2017, April). Neural collaborative filtering. In Proceedings of the 26th international conference on world wide web, 173-182.
  18. Hegde, S. B., Satyappanavar, S., & Setty, S. (2018). Sentiment based food classification for restaurant business. In 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 1455-1462.
  19. Hlee, S., Lee, J., Yang, S. B., & Koo, C. (2019). The moderating effect of restaurant type on hedonic versus utilitarian review evaluations. International Journal of Hospitality Management, 77, 195-206. https://doi.org/10.1016/j.ijhm.2018.06.030
  20. Horng, J. S., & Hsu, H. (2020). A holistic aesthetic experience model: Creating a harmonious dining environment to increase customers' perceived pleasure. Journal of Hospitality and Tourism Management, 45, 520-534. https://doi.org/10.1016/j.jhtm.2020.10.006
  21. Idrissi, N., & Zellou, A. (2020). A systematic literature review of sparsity issues in recommender systems. Social Network Analysis and Mining, 10(1), 1-23. https://doi.org/10.1007/s13278-019-0612-8
  22. Jain, A., Nagar, S., Singh, P. K., & Dhar, J. (2020). EMUCF: Enhanced multistage user-based collaborative filtering through non-linear similarity for recommendation systems. Expert Systems with Applications, 161, 113724.
  23. Jin, B., Gao, C., He, X., Jin, D., & Li, Y. (2020, July). Multi-behavior recommendation with graph convolutional networks. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 659-668.
  24. Kim, D., Park, C., Oh, J., Lee, S., & Yu, H. (2016). Convolutional matrix factorization for document context-aware recommendation. In Proceedings of the 10th ACM conference on recommender systems, 233-240.
  25. Kingma, D. P., & Ba, J. (2015). Adam: A Method for Stochastic Optimization. arXiv preprint arXiv:1412.6980.
  26. Koohi, H., & Kiani, K. (2016). User based collaborative filtering using fuzzy C-means. Measurement, 91, 134-139. https://doi.org/10.1016/j.measurement.2016.05.058
  27. Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8), 30-37. https://doi.org/10.1109/MC.2009.263
  28. Lee, M., Jeong, M., & Lee, J. (2017). Roles of negative emotions in customers' perceived helpfulness of hotel reviews on a user-generated review website: A text mining approach. International Journal of Contemporary Hospitality Management, 29(2), 762-783. https://doi.org/10.1108/IJCHM-10-2015-0626
  29. Li, Q., Li, X., Lee, B., & Kim, J. (2021). A Hybrid CNN-Based Review Helpfulness Filtering Model for Improving E-Commerce Recommendation Service. Applied Sciences, 11(18), 8613. https://www.mdpi.com/2076-3417/11/18/8613
  30. Li, X., Wang, M., & Liang, T.-P. (2014). A multitheoretical kernel-based approach to social network-based recommendation. Decision Support Systems, 65, 95-104.
  31. Lima, G. R., Mello, C. E., Lyra, A., & Zimbrao, G. (2020). Applying landmarks to enhance memory-based collaborative filtering. Information Sciences, 513, 412-428. https://doi.org/10.1016/j.ins.2019.10.041
  32. Loureiro, S. M. C., Almeida, M., & Rita, P. (2013). The effect of atmospheric cues and involvement on pleasure and relaxation: The spa hotel context. International Journal of Hospitality Management, 35, 35-43. https://doi.org/10.1016/j.ijhm.2013.04.011
  33. Lu, J., Wu, D., Mao, M., Wang, W., & Zhang, G. (2015). Recommender system application developments: a survey. Decision Support Systems, 74, 12-32. https://doi.org/10.1016/j.dss.2015.03.008
  34. Mahadi, M., Zainuddin, N., Shah, N., Naziron, N. A., & Rum, S. (2018). E-halal restaurant recommender system using collaborative filtering algorithm. Journal of Advanced Research in Computing and Applications, 12(1), 22-34.
  35. Miao, X., Gao, Y., Chen, G., Cui, H., Guo, C., & Pan, W. (2016). SI2P: A restaurant recommendation system using preference queries over incomplete information. Proceedings of the VLDB Endowment, 9(13), 1509-1512. https://doi.org/10.14778/3007263.3007296
  36. Nemade, G., Deshmane, R., Thakare, P., Patil, M., & Thombre, V. (2017). Smart tourism recommender system. International Research Journal of Engineering and Technology (IRJET), 4(11), 601-603.
  37. Nilashi, M., Ibrahim, O., & Bagherifard, K. (2018). A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques. Expert Systems with Applications, 92, 507-520. https://doi.org/10.1016/j.eswa.2017.09.058
  38. Onan, A. (2021). Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurrency and Computation: Practice and Experience, 33(23), e5909.
  39. Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1994, October). Grouplens: An open architecture for collaborative filtering of netnews. In Proceedings of the 1994 ACM conference on Computer supported cooperative work, 175-186.
  40. Sak, H., Senior, A., & Beaufays, F. (2014). Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition. arXiv preprint arXiv:1402.1128.
  41. Salehan, M., & Kim, D. J. (2016). Predicting the performance of online consumer reviews: A sentiment mining approach to big data analytics. Decision Support Systems, 81, 30-40. https://doi.org/10.1016/j.dss.2015.10.006
  42. Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001, April). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web, 285-295.
  43. Saumya, S., Singh, J. P., & Dwivedi, Y. K. (2020). Predicting the helpfulness score of online reviews using convolutional neural network. Soft Computing, 24(15), 10989-11005. https://doi.org/10.1007/s00500-019-03851-5
  44. Singh, M. (2020). Scalability and sparsity issues in recommender datasets: a survey. Knowledge and Information Systems, 62(1), 1-43. https://doi.org/10.1007/s10115-018-1254-2
  45. Unger, M., Tuzhilin, A., & Livne, A. (2020). Context-aware recommendations based on deep learning frameworks. ACM Transactions on Management Information Systems (TMIS), 11(2), 1-15. https://doi.org/10.1145/3386243
  46. Xue, H. J., Dai, X., Zhang, J., Huang, S., & Chen, J. (2017). Deep matrix factorization models for recommender systems. In IJCAI, 17, 3203-3209. https://doi.org/10.24963/ijcai.2017/447
  47. Yang, S., Yao, J., & Qazi, A. (2020). Does the review deserve more helpfulness when its title resembles the content? Locating helpful reviews by text mining. Information Processing & Management, 57(2), 102179.
  48. Yoo, S., Song, J., & Jeong, O. (2018). Social media contents based sentiment analysis and prediction system. Expert Systems with Applications, 105, 102-111. https://doi.org/10.1016/j.eswa.2018.03.055
  49. Yu, B., Zhou, J., Zhang, Y., & Cao, Y. (2017). Identifying restaurant features via sentiment analysis on yelp reviews. arXiv preprint arXiv:1709.08698.
  50. Yu, K., Schwaighofer, A., Tresp, V., Xu, X., & Kriegel, H.-P. (2004). Probabilistic memory-based collaborative filtering. IEEE Transactions on Knowledge and Data Engineering, 16(1), 56-69. https://doi.org/10.1109/TKDE.2004.1264822
  51. Yue, W., Wang, Z., Liu, W., Tian, B., Lauria, S., & Liu, X. (2021). An optimally weighted user-and item-based collaborative filtering approach to predicting baseline data for Friedreich's Ataxia patients. Neurocomputing, 419, 287-294. https://doi.org/10.1016/j.neucom.2020.08.031
  52. Zhang, H., Ganchev, I., Nikolov, N. S., Ji, Z., & O'Droma, M. (2021). FeatureMF: an item feature enriched matrix factorization model for item recommendation. IEEE Access, 9, 65266-65276. https://doi.org/10.1109/ACCESS.2021.3074365