Abstract
Tourism is an important industry and a popular entertainment activity involving billions of visitors per annum. One challenging problem tourists face is identifying satisfactory products from vast tourism information. Most of travel recommendation methods regard the recommendation procedure as a static process and only focus on immediate rewards. Meanwhile, they often infer user intensions from click behaviors and ignore the informative keywords of the clicked products. To this end, in this article, we present a Keywords-enhanced Deep Reinforcement Learning model (KDRL) framework. Specifically, we formalize travel recommendation as a Markov Decision Process and implement it upon the Actor–Critic framework. It integrates keyword information into the reinforcement learning–(RL) based recommendation framework by devising novel state representation and reward function and learns the travel recommendation and keywords generation simultaneously. To the best of our knowledge, this is the first time that keywords are explicitly discussed and used in RL-based travel recommendations. Extensive experiments are performed on the real-world datasets and the results clearly show the superior performance of KDRL compared with the baseline methods.
- [1] . 2022. Holistic combination of structural and textual code information for context based api recommendation. IEEE Trans. Softw. Eng. 48, 8 (2022), 2987–3009.Google Scholar
Digital Library
- [2] . 2022. Multi-view graph attention network for travel recommendation. Expert Syst. Appl. 191, 11 (2022), 116234.Google Scholar
Digital Library
- [3] . 2020. Travel recommendation via fusing multi-auxiliary information into matrix factorization. ACM Trans. Intell. Syst. Technol. 11, 2 (2020), 1–24.Google Scholar
Digital Library
- [4] . 2021. Reinforcement recommendation with user multi-aspect preference. In Proceedings of the International Conference on World Wide Web. 425–435.Google Scholar
Digital Library
- [5] . 2019. Generative adversarial user model for reinforcement learning based recommendation system. In Proceedings of the International Conference on Machine Learning. PMLR, 1052–1061.Google Scholar
- [6] . 2019. Dynamic explainable recommendation based on neural attentive models. In Proceedings of the AAAI Conference on Artificial Intelligence. 53–60.Google Scholar
Digital Library
- [7] . 2021. Hybrid-order gated graph neural network for session-based recommendation. IEEE Trans. Industr. Inf. 18, 3 (2021), 1458–1467.Google Scholar
Cross Ref
- [8] . 2021. Curriculum meta-learning for next POI recommendation. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2692–2702.Google Scholar
Digital Library
- [9] . 2022. A learning-based POI recommendation with spatiotemporal context awareness. IEEE Trans. Cybernet. 52, 4 (2022), 2453–2466.Google Scholar
Cross Ref
- [10] . 2020. Recurrent thrifty attention network for remote sensing scene recognition. IEEE Trans. Geosci. Remote Sens. 59, 10 (2020), 8257–8268.Google Scholar
Cross Ref
- [11] . 2022. TRACE: Travel reinforcement recommendation based on location-aware context extraction. ACM Trans. Knowl. Discov. Data 16, 4 (2022), 1–22.Google Scholar
Digital Library
- [12] . 2014. Cost-aware collaborative filtering for travel tour recommendations. ACM Trans. Inf. Syst. 32, 1 (2014), 1–31.Google Scholar
Digital Library
- [13] . 2016. SocoTraveler: Travel-package recommendations leveraging social influence of different relationship types. Inf. Manage. 53, 8 (2016), 934–950.Google Scholar
Digital Library
- [14] . 2018. Recurrent neural networks with top-k gains for session-based recommendations. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management. 843–852.Google Scholar
Digital Library
- [15] . 2019. Higher-order multi-layer community detection. In Proceedings of the AAAI Conference on Artificial Intelligence. 9945–9946.Google Scholar
Digital Library
- [16] . 2021. Deep inclusion relation-aware network for user response prediction at fliggy. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3059–3067.Google Scholar
Digital Library
- [17] . 2020. A hybrid context-aware approach for e-tourism package recommendation based on asymmetric similarity measurement and sequential pattern mining. Electr. Commerce Res. Appl. 42, 5 (2020), 100978.Google Scholar
Cross Ref
- [18] . 2020. STP-UDGAT: Spatial-temporal-preference user dimensional graph attention network for next POI recommendation. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 845–854.Google Scholar
Digital Library
- [19] . 2021. Noninvasive self-attention for side information fusion in sequential recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence. 4249–4256.Google Scholar
Cross Ref
- [20] . 2020. Dynamic attention-based explainable recommendation with textual and visual fusion. Inf. Process. Manage. 57, 6 (2020), 102099.Google Scholar
Cross Ref
- [21] . 2020. Keywords generation improves e-commerce session-based recommendation. In Proceedings of the International Conference on World Wide Web. 1604–1614.Google Scholar
Digital Library
- [22] . 2021. Stan: Spatio-temporal attention network for next location recommendation. In Proceedings of the 30th International Conference on World Wide Web. 2177–2185.Google Scholar
Digital Library
- [23] . 2019. SDM: Sequential deep matching model for online large-scale recommender system. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 2635–2643.Google Scholar
Digital Library
- [24] . 2009. BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence. 452–461.Google Scholar
Digital Library
- [25] . 2020. How useful are reviews for recommendation? A critical review and potential improvements. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 1845–1848.Google Scholar
Digital Library
- [26] . 2001. Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th International Conference on World Wide Web. 285–295.Google Scholar
Digital Library
- [27] . 2022. Choosing the best of both worlds: Diverse and novel recommendations through multi-objective reinforcement learning. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining. 957–965.Google Scholar
Digital Library
- [28] . 2020. Dual learning for explainable recommendation: Towards unifying user preference prediction and review generation. In Proceedings of the 29th International Conference on World Wide Web. 837–847.Google Scholar
Digital Library
- [29] . 2021. Cost-effective and interpretable job skill recommendation with deep reinforcement learning. In Proceedings of the 30th International Conference on World Wide Web. 3827–3838.Google Scholar
Digital Library
- [30] . 2018. Travel itinerary recommendations with must-see points-of-interest. In Companion of the The Web Conference on The Web Conference. International World Wide Web Conferences Steering Committee, 1198–1205.Google Scholar
Digital Library
- [31] . 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998–6008.Google Scholar
- [32] . 2015. Collaborative deep learning for recommender systems. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1235–1244.Google Scholar
Digital Library
- [33] . 2019. Session-based recommendation with graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence. 346–353.Google Scholar
Digital Library
- [34] . 2022. Deep rating and review neural network for item recommendation. IEEE Trans. Neural Netw. Learn. Syst. 33, 11 (2022), 6726–6736.Google Scholar
Cross Ref
- [35] . 2021. Hierarchical reinforcement learning for integrated recommendation. In Proceedings of the AAAI Conference on Artificial Intelligence. 4521–4528.Google Scholar
Cross Ref
- [36] . 2021. Itinerary-aware personalized deep matching at fliggy. In Proceedings of the International Conference on World Wide Web. 3234–3245.Google Scholar
Digital Library
- [37] . 2021. Multiview learning with robust double-sided twin SVM. IEEE Trans. Cybernet. 52, 11 (2021), 11963–11976.Google Scholar
- [38] . 2020. A category-aware deep model for successive POI recommendation on sparse check-in data. In Proceedings of the 29th International Conference on World Wide Web. 1264–1274.Google Scholar
Digital Library
- [39] . 2021. CHA: Categorical hierarchy-based attention for next POI recommendation. ACM Trans. Inf. Syst. 40, 1 (2021), 1–22.Google Scholar
Digital Library
- [40] . 2021. Intelligent electric vehicle charging recommendation based on multi-agent reinforcement learning. In Proceedings of the 2021 International Conference on World Wide Web. 1856–1867.Google Scholar
Digital Library
- [41] . 2021. Combining explicit entity graph with implicit text information for news recommendation. In Proceedings of the International Conference on World Wide Web. 412–416.Google Scholar
Digital Library
- [42] . 2020. Mahrl: Multi-goals abstraction based deep hierarchical reinforcement learning for recommendations. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 871–880.Google Scholar
Digital Library
- [43] . 2020. Whole-chain recommendations. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 1883–1891.Google Scholar
Digital Library
- [44] . 2018. DRN: A deep reinforcement learning framework for news recommendation. In Proceedings of the World Wide Web Conference. 167–176.Google Scholar
Digital Library
- [45] . 2020. Multimodal summarization with guidance of multimodal reference. In Proceedings of the AAAI Conference on Artificial Intelligence. 9749–9756.Google Scholar
Cross Ref
Index Terms
Keywords-enhanced Deep Reinforcement Learning Model for Travel Recommendation
Recommendations
Trip Reinforcement Recommendation with Graph-based Representation Learning
Tourism is an important industry and a popular leisure activity involving billions of tourists per annum. One challenging problem tourists face is identifying attractive Places-of-Interest (POIs) and planning the personalized trip with time constraints. ...
Multi-objective reinforcement learning approach for trip recommendation
AbstractTrip recommendation is an intelligent service that provides personalized itinerary plans for tourists in unfamiliar cities. It aims to construct a series of ordered POIs that maximizes user travel experiences with temporal and spatial ...
Highlights- We propose a multi-objective reinforcement learning for trip recommendation.
- We ...
CapDRL: A Deep Capsule Reinforcement Learning for Movie Recommendation
PRICAI 2019: Trends in Artificial IntelligenceAbstractRecommender systems provide users with a personalized list based on individual interests. There are three main challenges in traditional movie recommendation models: (1) considering recommendation procedure as a static one; (2) not taking user’s ...






Comments