The attraction recommendation systems not only filter out overwhelming irrelevant information for visitors but also identify potential customers for service providers. However, the current attraction recommendation methods such as content-based methods, collaborative filtering, or deep learning-based methods are either inaccurate due to data sparsity, or lack of interpretability, which results in the users' suspicion on the recommendation results. To address the limitations of the current methods, we introduce a novel framework for preference propagation on knowledge graphs (KGs), which utilizes lots of parameters to capture the abundant semantics of existing KGs more comprehensively, and meanwhile explains the results through reasoning the link paths from user's history to candidates on KGs. With a multi-view spatiotemporal analysis on real-world travel data, we investigate the geographical characteristics of human tour activities and build a tourism-oriented KG based on open web resources. Then, we propose a KG-aware attraction recommendation method named Geo-RippleNet and implement it with extensive experiments on large-scale datasets. It is argued that the framework for preference propagation on KGs not only absorb rich semantic information to achieve substantial performance gains in the attraction recommendation scenario but also enhance the interpretability of recommendation results with the support of abundant relational knowledge. Moreover, incorporating the spatiotemporal characteristics of human tour activities into the framework for preference propagation further makes the recommendation performance more aligned with the potential interests of visitors.
国家自然科学基金项目(41631177,41801320)
[1] Ricci F, Rokach L, Shapira B. Recommender systems: introduction and challenges. In: Recommender Systems Handbook. Berlin: Springer, 2015. Google Scholar
[2] Yeh D Y, Cheng C H. Recommendation system for popular tourist attractions in Taiwan using Delphi panel and repertory grid techniques. Tourism Manage, 2015, 46: 164-176 CrossRef Google Scholar
[3] Pazzani M J, Billsus D. Content-based recommendation systems. In: Proceedings of the Adaptive Web, 2007. 325--341. Google Scholar
[4] Herlocker J L, Konstan J A, Borchers A, et al. An algorithmic framework for performing collaborative filtering. In: Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 1999. Google Scholar
[5] Elkahky A, Song Y, He X D. A multi-view deep learning approach for cross domain user modeling in recommendation systems. In: Proceedings of the 24th International Conference on World Wide Web, 2015. Google Scholar
[6] Shwartz-Ziv R, Tishby N. Opening the black box of deep neural networks via information. 2017,. arXiv Google Scholar
[7] Lin Y K, Liu Z Y, Sun M S, et al. Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence, 2015. Google Scholar
[8] Wang H W, Zhang F Z, Wang J L, et al. Ripplenet: propagating user preferences on the knowledge graph for recommender systems. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018. Google Scholar
[9] Petronis K R. A different kind of contextual effect: geographical clustering of cocaine incidence in the USA. J Epidemiology Community Health, 2003, 57: 893-900 CrossRef Google Scholar
[10] Soja E W. Regions in context: spatiality, periodicity, and the historical geography of the regional question. Environ Plann D, 1985, 3: 175-190 CrossRef Google Scholar
[11] Mathias M, Zhou F, Torres-Moreno J M. Personalized sightseeing tours: a model for visits in art museums. Int J Geographical Inf Sci, 2017, 31: 591-616 CrossRef Google Scholar
[12] Gras B, Brun A, Boyer A. Identifying grey sheep users in collaborative filtering: a distribution-based technique. In: Proceedings of Conference on User Modeling Adaptation and Personalization, 2016. Google Scholar
[13] Wang R X, Fu B, Fu G, et al. Deep & cross network for ad click predictions. In: Proceedings of Knowledge Discovery and Data Mining, 2017. Google Scholar
[14] Guo H F, Tang R M, Ye Y M, et al. DeepFM: a factorization-machine based neural network for CTR prediction. 2017,. arXiv Google Scholar
[15] Choi C, Cho M, Choi J, et al. Travel ontology for intelligent recommendation system. In: Proceedings of the 3rd Asia International Conference on Modelling & Simulation, 2009. Google Scholar
[16] Daramola J O, Adigun M O, Ayo C K. Building an ontology-based framework for tourism recommendation services. In: Proceedings of Information Communication Technologies in Tourism, 2009. 135--147. Google Scholar
[17] Lu C, Laublet P, Stankovic M. Travel attractions recommendation with knowledge graphs. In: Proceedings of Knowledge Acquisition, Modeling and Management, 2016. Google Scholar
[18] Sun Y Z, Han J W, Yan X F, et al, Pathsim: meta path-based top-k similarity search in heterogeneous information networks. In: Proceedings of Very Large Data Bases, 2011. 992--1003. Google Scholar
[19] Yu X, Ren X, Sun Y Z, et al. Personalized entity recommendation: a heterogeneous information network approach. In: Proceedings of the 7th ACM International Conference on Web Search and Data Mining, 2014. Google Scholar
[20] Wang Q, Mao Z, Wang B. Knowledge Graph Embedding: A Survey of Approaches and Applications. IEEE Trans Knowl Data Eng, 2017, 29: 2724-2743 CrossRef Google Scholar
[21] Wang H W, Zhang F Z, Zhao M, et al. Multi-task feature learning for knowledge graph enhanced recommendation. In: Proceedings of World Wide Web Conference, 2019. Google Scholar
[22] Brockmann D, Hufnagel L, Geisel T. The scaling laws of human travel. Nature, 2006, 439: 462-465 CrossRef ADS arXiv Google Scholar
[23] Cleveland R B, Cleveland W S, Mcrae J E, et al. STL: a seasonal-trend decomposition procedure based on LOESS. J Off Stat, 1990, 6: 3--33. Google Scholar
[24] Xu B, Xu Y, Liang J Q, et al. CN-DBpedia: a never-ending chinese knowledge extraction system. In: Proceedings of International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, 2017. Google Scholar
Figure 1
(Color online) The influence of travel distance on the visiting intention of attractions
Figure 2
(Color online) The relationship between the co-occurrence probability and relative distance of attractions
Figure 3
(Color online) The periodic decomposition of travel behavior
Figure 4
(Color online) The off-peak season distribution of tourists to attractions
Figure 5
(Color online) The framework of Geo-RippleNet
Figure 6
(Color online) (a) The framework diagram and (b) the demo of tourism knowledge graph
Figure 7
(Color online) The result of the optimal recommendation set. (a) Precision@K; (b) Recall@K; (c) F1@K
Figure 8
(Color online) The case study
| Model | AUC | Accuracy |
| CB | 0.504 | 0.499 |
| CF | 0.782 | 0.501 |
| Wide&Deep | 0.855 | 0.773 |
| Geo-RankFM | 0.837 | 0.754 |
| RippleNet | 0.912 | 0.821 |
| Geo-RippleNet | 0.928 | 0.852 |
| Model | AUC | Accuracy |
| RippleNet | 0.912 | 0.821 |
| Space-RippleNet | 0.921 | 0.839 |
| Temp-RippleNet | 0.918 | 0.831 |
| Geo-RippleNet | 0.928 | 0.852 |
Copyright 2020 CHINA SCIENCE PUBLISHING & MEDIA LTD. 中国科技出版传媒股份有限公司 版权所有
京ICP备14028887号-23 京公网安备11010102003388号
Download PDF
