TRACE: Travel Reinforcement Recommendation Based on Location-Aware Context Extraction
TRACE: Travel Reinforcement Recommendation Based on Location-Aware Context Extraction
复制标题
DOI：
10.1145/3487047
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Zhe Fu;Li Yu;Xichuan Niu
中科院分区：
文献类型：
--
作者：
Zhe Fu;Li Yu;Xichuan Niu
随着在线旅游平台的普及，用户倾向于临时决定要去的地方，而不是提前准备详细的旅游计划。在用户需求具有时效性和不确定性的情况下，如何将实时上下文信息融入到动态个性化推荐中成为旅游推荐系统的关键问题。在本文中，通过整合用户的历史偏好和实时上下文，一个位置感知的推荐系统称为TRACE（基于位置的T ravel R einstruments Recommendations Based on Location-A ware C ontext E extraction）。它基于位置感知的上下文学习模型捕捉用户特征，并基于强化学习进行动态推荐。具体来说，这项研究：（1）设计了一个基于Actor-Critic框架的旅游强化推荐系统，该系统能够动态跟踪用户偏好的变化，优化推荐系统的性能;（2）提出了一个位置感知的上下文学习模型，该模型旨在从实时位置中提取用户上下文，然后计算附近景点对用户偏好的影响;（3）进行了离线和在线实验。我们提出的模型在两个实验中都取得了最好的性能，这表明基于实时位置跟踪用户的偏好变化对于改善推荐结果是有价值的。
As the popularity of online travel platforms increases, users tend to make ad-hoc decisions on places to visit rather than preparing the detailed tour plans in advance. Under the situation of timeliness and uncertainty of users’ demand, how to integrate real-time context into dynamic and personalized recommendations have become a key issue in travel recommender system. In this article, by integrating the users’ historical preferences and real-time context, a location-aware recommender system called TRACE ( T ravel R einforcement Recommendations Based on Location- A ware C ontext E xtraction) is proposed. It captures users’ features based on location-aware context learning model, and makes dynamic recommendations based on reinforcement learning. Specifically, this research: (1) designs a travel reinforcing recommender system based on an Actor-Critic framework, which can dynamically track the user preference shifts and optimize the recommender system performance; (2) proposes a location-aware context learning model, which aims at extracting user context from real-time location and then calculating the impacts of nearby attractions on users’ preferences; and (3) conducts both offline and online experiments. Our proposed model achieves the best performance in both of the two experiments, which demonstrates that tracking the users’ preference shifts based on real-time location is valuable for improving the recommendation results.