Information Systems Review (경영정보학연구)

The Korea Society of Management Information Systems (한국경영정보학회)
권호 표지
DOI QR코드

DOI QR Code

Developing a Deep Learning-based Restaurant Recommender System Using Restaurant Categories and Online Consumer Review

레스토랑 카테고리와 온라인 소비자 리뷰를 이용한 딥러닝 기반 레스토랑 추천 시스템 개발

  • Haeun Koo (Department of Big Data Analytics, Kyung Hee University) ;
  • Qinglong Li (Department of Big Data Analytics, Kyung Hee University) ;
  • Jaekyeong Kim (School of Management & Department of Big Data Analytics, Kyung Hee University)
  • 구하은 (경희대학교 빅데이터응용학과) ;
  • 이청용 (경희대학교 빅데이터응용학과) ;
  • 김재경 (경희대학교 경영대학 & 빅데이터응용학과)
  • Received : 2022.11.01
  • Accepted : 2022.12.08
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Research on restaurant recommender systems has been proposed due to the development of the food service industry and the increasing demand for restaurants. Existing restaurant recommendation studies extracted consumer preference information through quantitative information or online review sensitivity analysis, but there is a limitation that it cannot reflect consumer semantic preference information. In addition, there is a lack of recommendation research that reflects the detailed attributes of restaurants. To solve this problem, this study proposed a model that can learn the interaction between consumer preferences and restaurant attributes by applying deep learning techniques. First, the convolutional neural network was applied to online reviews to extract semantic preference information from consumers, and embedded techniques were applied to restaurant information to extract detailed attributes of restaurants. Finally, the interaction between consumer preference and restaurant attributes was learned through the element-wise products to predict the consumer preference rating. Experiments using an online review of Yelp.com to evaluate the performance of the proposed model in this study confirmed that the proposed model in this study showed excellent recommendation performance. By proposing a customized restaurant recommendation system using big data from the restaurant industry, this study expects to provide various academic and practical implications.

최근에는 외식 산업의 발달과 레스토랑 수요의 증가로 인해 레스토랑 추천 시스템 연구가 활발하게 제안되고 있다. 기존 레스토랑 추천 시스템 연구는 정량적인 평점 정보 또는 온라인 리뷰의 감성분석을 통해 소비자의 선호도 정보를 추출하였는데 이는 소비자의 의미론적 선호도 정보는 반영하지 못한다는 한계가 존재한다. 또한, 레스토랑이 포함하는 세부적인 속성을 반영한 추천 시스템 연구는 부족한 실정이다. 이를 해결하기 위해 본 연구에서는 소비자의 선호도와 레스토랑 속성 간의 상호작용을 효과적으로 학습할 수 있는 딥러닝 기반 모델을 제안하였다. 먼저, 합성곱 신경망을 온라인 리뷰에 적용하여 소비자의 의미론적 선호도 정보를 추출했고, 레스토랑 정보에 임베딩 기법을 적용하여 레스토랑의 세부적인 속성을 추출했다. 최종적으로 요소별 연산을 통해 소비자 선호도와 레스토랑 속성 간의 상호작용을 학습하여 소비자의 선호도 평점을 예측했다. 본 연구에서 제안한 모델의 추천 성능을 평가하기 위해 Yelp.com의 온라인 리뷰를 사용한 실험 결과, 기존 연구의 다양한 모델과 비교했을때 본 연구의 제안 모델이 우수한 추천 성능을 보이는 것을 확인하였다. 본 연구는 레스토랑 산업의 빅데이터를 활용한 맞춤형 레스토랑 추천 시스템을 제안함으로써 레스토랑 연구 분야와 온라인 서비스 제공자에게 학술적 및 실무적 측면에서 다양한 시사점을 제공할 수 있을 것으로 기대한다.

Keywords

Acknowledgement

본 논문은 교육부 및 한국연구재단 4단계 두뇌한국21 사업(4단계 BK21 사업)으로부터 지원받은 연구임.

References

  1. 구민정, 안현철, "종합 평점과 다기준 평점을 선택적으로 활용하는 협업필터링 기반 하이브리드 추천시스템", 지능정보연구, 제24권, 제2호, 2018, pp. 85-109. https://doi.org/10.13088/JIIS.2018.24.2.085
  2. 김윤진, "세계 외식산업 성장과 트렌드", 세계농업, 제168권, 2014, pp. 115-128.
  3. 나진성, 노용휘, "네트워크 텍스트 분석을 통한 외식경영 연구동향 분석: 최근 3개년(2012년도-2014년도) 논문을 중심으로", 외식경영 연구, 제18권, 제1호, 2015, pp. 117-136.
  4. 박호연, 김경재, "CNN-LSTM 조합모델을 이용한 영화리뷰 감성분석", 지능정보연구, 제25권, 제4호, 2019, pp. 141-154. https://doi.org/10.13088/JIIS.2019.25.4.141
  5. 손지은, 김성범, 김현중, 조성준, "추천시스템기법 연구동향 분석", 대한산업공학회지, 제41권, 제2호, 2015, pp. 185-208. https://doi.org/10.7232/JKIIE.2015.41.2.185
  6. 이륜경, 정남호, 홍태호, "딥러닝을 이용한 온라인 리뷰 기반 다속성별 추천 모형 개발", 정보시스템연구, 제28권, 제1호, 2019, pp.97-114.
  7. 이청용, 이병현, 이흠철, 김재경, "CNN 기반 리뷰 유용성 점수 예측을 통한 개인화 추천 서비스 성능 향상에 관한 연구", 지능정보연구, 제27권, 제3호, 2021, pp. 29-56. https://doi.org/10.13088/JIIS.2021.27.3.029
  8. 이흠철, 윤효림, 이청용, 김재경, "Multi-channel CNN 기반 온라인 리뷰 유용성 예측 모델 개발에 관한 연구", 지능정보연구, 제28권, 제2호, 2022, pp. 171-189. https://doi.org/10.13088/JIIS.2022.28.2.171
  9. 조승연, 최지은, 이규현, 김희웅, "고객 온라인 구매후기를 활용한 추천 시스템 개발 및 적용", Information Systems Review, 제17권, 제3호, 2015, pp. 95-111. https://doi.org/10.14329/isr.2015.17.3.095
  10. 홍민성, 정남호, 한석호, "딥러닝 기반 스마트 관광 추천 알고리즘 개발 연구: 새로운 OTA 레스토랑 추천 시스템의 제안", 관광레저연구, 제34권, 제3호, 2022, pp. 431-444. https://doi.org/10.31336/JTLR.2022.3.34.3.431
  11. Alashkar, T., S. Jiang, S. Wang, and Y. Fu, "Examples-rules guided deep neural network for makeup recommendation", Proceedings of the AAAI Conference on Artificial Intelligence, 2017, pp. 941-947.
  12. Amari, S., The handbook of brain theory and neural networks, MIT Press, Cambridge, Massachusetts, U.S., 2003.
  13. Asani, E., H. Vahdat-Nejad, and J. Sadri, "Restaurant recommender system based on sentiment analysis", Machine Learning with Applications, Vol. 6, 2021, pp. 100-114. https://doi.org/10.1016/j.mlwa.2021.100114
  14. Behera, G. and N. Nain, "Handling data sparsity via item metadata embedding into deep collaborative recommender system", Journal of King Saud University-Computer and Information Sciences, 2022, pp. 9953-9963.
  15. Billsus, D. and M. J. Pazzani, "Learning collaborative information filters", International Conference on Machine Learning (ICML), Vol. 98, 1998, pp. 46-54.
  16. Chen, C., P. Zhao, L. Li, J. Zhou, X. Li, and M. Qiu, "Locally connected deep learning framework for industrial-scale recommender systems", Proceedings of the 26th International Conference on World Wide Web Companion, 2017, pp. 769-770.
  17. Cho, Y. H., J. K. Kim, and S. H. Kim, "A personalized recommender system based on web usage mining and decision tree induction", Expert Systems with Applications, Vol. 23, No. 3, 2002, pp. 329-342. https://doi.org/10.1016/S0957-4174(02)00052-0
  18. Dalvi, R. R., S. B. Chavan, and A. Halbe, "Detecting a Twitter cyberbullying using machine learning", 4th International Conference on Intelligent Computing and Control Systems (ICICCS), 2020, pp. 297-301.
  19. Denny, M. J. and A. Spirling, "Text preprocessing for unsupervised learning: Why it matters, when it misleads, and what to do about it", Political Analysis, Vol. 26, No. 2, 2018, pp. 168-189. https://doi.org/10.1017/pan.2017.44
  20. Dong, J., F. He, Y. Guo, and H. Zhang, "A commodity review sentiment analysis based on BERT-CNN model", 2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020, pp. 143-147.
  21. Du, J., L. Zheng, J. He, J. Rong, H. Wang, and Y. Zhang, "An interactive network for end-to-end review helpfulness modeling", Data Science and Engineering, Vol. 5, No. 3, 2020, pp. 261-279. https://doi.org/10.1007/s41019-020-00133-1
  22. Gamon, M., A. Aue, S. Corston-Oliver, and E. Ringger, "Pulse: Mining customer opinions from free text", Proceedings of 6th International Symposium on Intelligent Data Analysis, 2005, pp. 121-132.
  23. Goldberg, K., T. Roeder, D. Gupta, and C. Perkins, "Eigentaste: A constant time collaborative filtering algorithm", Information Retrieval, Vol. 4, No. 2, 2001, pp. 133-151. https://doi.org/10.1023/A:1011419012209
  24. He, X. and T.-S. Chua, "Neural factorization machines for sparse predictive analytics", Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017, pp. 355-364.
  25. He, X., L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua, "Neural collaborative filtering", Proceedings of the 26th International Conference on World Wide Web, 2017, pp.173-182.
  26. Hegde, S. B., S. Satyappanavar, and S. Setty, "Sentiment based food classification for restaurant business", 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018, pp. 1455-1462.
  27. Herlocker, J. L., J. A. Konstan, A. Borchers, and J. Riedl, "An algorithmic framework for performing collaborative filtering", Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1999, pp. 230-237.
  28. Iwendi, C., E. Ibeke, H. Eggoni, S. Velagala, and G. Srivastava, "Pointer-based item-to-item collaborative filtering recommendation system using a machine learning model", International Journal of Information Technology & Decision Making, Vol. 21, No. 01, 2022, pp. 463-484.
  29. Kang, S., J. Hwang, W. Kweon, and H. Yu, "DE-RRD: A knowledge distillation framework for recommender system", Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2020, pp. 605-614.
  30. Kaur, S., P. Kumar, and P. Kumaraguru, "Detecting clickbaits using two-phase hybrid CNN-LSTM biterm model", Expert Systems with Applications, Vol. 151, 2020, pp. 113350.
  31. Kiran, R., P. Kumar, and B. Bhasker, "DNNRec: A novel deep learning based hybrid recommender system", Expert Systems with Applications, Vol. 144, 2020, pp. 113054.
  32. Lee, D., Hosanagar, K., "How do recommender systems affect sales diversity? A cross-category investigation via randomized field experiment", Information Systems Research, Vol. 30, No. 1, 2019, pp. 239-259. https://doi.org/10.1287/isre.2018.0800
  33. Li, L., Y. Zhou, H. Xiong, Hu, C., Wei, X., "Collaborative filtering based on user attributes and user ratings for restaurant recommendation", 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2017, pp. 2592-2597.
  34. Liu, J., C. Wu, and W. Liu, "Bayesian probabilistic matrix factorization with social relations and item contents for recommendation", Decision Support Systems, Vol. 55, No. 3, 2013, pp. 838-850. https://doi.org/10.1016/j.dss.2013.04.002
  35. Liu, Z., B. Yuan, and Y. Ma, "A multi-task dual attention deep recommendation model using ratings and review helpfulness", Applied Intelligence, Vol. 52, No. 5, 2022, pp. 5595-5607. https://doi.org/10.1007/s10489-021-02666-y
  36. Lu, J., D. Wu, M. Mao, W. Wang, and G. Zhang, "Recommender system application developments: A survey", Decision Support Systems, Vol. 74, 2015, pp. 12-32. https://doi.org/10.1016/j.dss.2015.03.008
  37. Majumder, N., S. Poria, A. Gelbukh, and E. Cambria, "Deep learning-based document modeling for personality detection from text", IEEE Intelligent Systems, Vol. 32, No. 2, 2017, pp. 74-79. https://doi.org/10.1109/MIS.2017.23
  38. Margaris, D., C. Vassilakis, and D. Spiliotopoulos, "What makes a review a reliable rating in recommender systems?", Information Processing & Management, Vol. 57, No. 6, 2020, pp. 102304.
  39. Muhammad, K., Q. Wang, D. O'Reilly-Morgan, E. Tragos, B. Smyth, N. Hurley, J. Geraci, and A. Lawlor, "Fedfast: Going beyond average for faster training of federated recommender systems", Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020, pp. 1234-1242.
  40. Nemade, G., R. Deshmane, P. Thakare, M. Patil, and V. Thombre, "Smart tourism recommender system", International Research Journal of Engineering and Technology (IRJET), Vol. 4, No. 11, 2017, pp. 601-603.
  41. Ning, X. and G. Karypis, "Slim: Sparse linear methods for top-n recommender systems", 2011 IEEE 11th International Conference on Data Mining, 2011, pp. 497-506.
  42. Park, D. H., H. K. Kim, I. Y. Choi, and J. K. Kim, "A literature review and classification of recommender systems research", Expert Systems with Applications, Vol. 39, No. 11, 2012, pp. 10059-10072. https://doi.org/10.1016/j.eswa.2012.02.038
  43. Radiuk, P. M., "Impact of training set batch size on the performance of convolutional neural networks for diverse datasets", Information Technology and Management Science, Vol. 20, No. 1, 2017, pp. 20-24. https://doi.org/10.1515/itms-2017-0003
  44. Raj, D., S. Sahu, and A. Anand, "Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text", Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), 2017, pp. 311-321.
  45. Rajendran, D. P. D., and R. P. Sundarraj, "Using topic models with browsing history in hybrid collaborative filtering recommender system: Experiments with user ratings", International Journal of Information Management Data Insights, Vol. 1, No. 2, 2021, pp. 100027.
  46. Ramachandran, D., and R. Parvathi, "Analysis of twitter specific preprocessing technique for tweets", Procedia Computer Science, Vol. 165, 2019, pp. 245-251. https://doi.org/10.1016/j.procs.2020.01.083
  47. Rendle, S., "Learning recommender systems with adaptive regularization", Proceedings of the 15th ACM International Conference on Web Search and Data Mining, 2012, pp. 133-142.
  48. Sarwar, B., G. Karypis, J. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms", Proceedings of the 10th International Conference on World Wide Web, 2001, pp. 285-295.
  49. Scaffidi, C., K. Bierhoff, E. Chang, M. Felker, H. Ng, and C. Jin, "Red Opal: product-feature scoring from reviews", Proceedings of the 8th ACM Conference on Electronic Commerce, 2007, pp. 182-191.
  50. She, X. and D. Zhang, "Text classification based on hybrid CNN-LSTM hybrid model", 2018 11th International Symposium on Computational Intelligence and Design (ISCID), 2018, pp. 184-189.
  51. Shi, Y., Q. Zhao, Y. Wang, and J. Cao, "An Improved Restaurant Recommendation Algorithm Based on User's Multiple Features", 2018 IEEE 9th International Conference on Software Engineering and Service Science (ICSESS), 2018, pp. 191-194.
  52. Silveira, T., M. Zhang, X. Lin, Y. Liu, and S. Ma, "How good your recommender system is? A survey on evaluations in recommendation", International Journal of Machine Learning and Cybernetics, Vol. 10, No. 5, 2019, pp. 813-831. https://doi.org/10.1007/s13042-017-0762-9
  53. Singh, R., J. Woo, N. Khan, J. Kim, H. Lee, H. Rahman, J. Park, J. Suh, M. Eom, N. Gudigantala, "Applications of machine learning models on Yelp data", Asia Pacific Journal of Information Systems, Vol. 29, No. 1, 2019, pp. 117-143. https://doi.org/10.14329/apjis.2019.29.1.35
  54. Sohrabi, M. K. and F. Hemmatian, "An efficient preprocessing method for supervised sentiment analysis by converting sentences to numerical vectors: a twitter case study", Multimedia Tools and Applications, Vol. 78, No. 17, 2019, pp. 24863-24882. https://doi.org/10.1007/s11042-019-7586-4
  55. Su, X. and T. M. Khoshgoftaar, "A survey of collaborative filtering techniques", Advances in Artificial Intelligence, 2009, pp. 1-19.
  56. Sun, L., J. Guo, and Y. Zhu, "Applying uncertainty theory into the restaurant recommender system based on sentiment analysis of online Chinese reviews", World Wide Web, Vol. 22, No. 1, 2019, pp. 83-100. https://doi.org/10.1007/s11280-018-0533-x
  57. Wang, H., D. Amagata, T. Maekawa, T. Hara, H. Niu, K. Yonekawa, and M. Kurokawa, "Preliminary investigation of alleviating user cold-start problem in e-commerce with deep cross-domain recommender system", Proceedings of the 2019 World Wide Web Conference, 2019, pp. 398-403.
  58. Wolfe, K., C. H. Hsu, and S. K. Kang, "Buyer characteristics among users of various travel intermediaries", Journal of Travel & Tourism Marketing, Vol. 17, No. 2-3, 2005, pp. 51-62. https://doi.org/10.1300/J073v17n02_05
  59. Wu, B., L. Zhong, H. Li, and Y. Ye, "Efficient complementary graph convolutional network without negative sampling for item recommendation", Knowledge-Based Systems, Vol. 256, 2022, pp. 109758.
  60. Wu, Y., C. DuBois, A. X. Zheng, and M. Ester, "Collaborative denoising auto-encoders for top-n recommender systems", Proceedings of the 9th ACM International Conference on Web Search and Data Mining, 2016, pp. 153-162.
  61. Yang, L., Y. Li, J. Wang, and R. S. Sherratt, "Sentiment analysis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning", IEEE Access, Vol. 8, 2020, pp. 23522-23530. https://doi.org/10.1109/ACCESS.2020.2969854
  62. Yoon, K., "Convolutional Neural Networks for Sentence Classification", Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014, pp. 1746-1751.
  63. Zhao, G., X. Qian, and H. Feng, "Personalized recommendation by exploring social users' behaviors", International Conference on Multimedia Modeling, 2014, pp. 181-191.
  64. Zhou, X., J. He, G. Huang, and Y. Zhang, "SVD-based incremental approaches for recommender systems", Journal of Computer and System Sciences, Vol. 81, No. 4, 2015, pp. 717-733.  https://doi.org/10.1016/j.jcss.2014.11.016