Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs
Modeling User Activity Preference by Leveraging User Spatial Temporal Characteristics in LBSNs
复制标题
DOI：
10.1109/tsmc.2014.2327053
复制
发表时间：
2015-01-01
影响因子：
8.7
通讯作者：
Yu, Zhiyong
中科院分区：
文献类型：
--
作者：
Yang, Dingqi;Zhang, Daqing;Yu, Zhiyong
随着最近基于位置的社交网络（LBSN）的激增，数百万用户的活动数据已经变得可获得。这些数据不仅包含用户活动的空间和时间戳，而且还包含其语义信息。LBSNs可以帮助理解移动的用户的时空活动偏好（STAP），这可以实现广泛的普适应用，例如个性化上下文感知位置推荐和面向群组的广告。然而，对这种用户特定的STAP进行建模需要处理高维数据，即，用户-位置-时间-活动四倍，这是复杂的并且通常遭受数据稀疏问题。为了解决这个问题，我们提出了一个STAP模型。该方法首先对空间和时间活动偏好分别建模，然后采用原则性的方法将二者联合收割机进行偏好推理。为了刻画空间特征对用户活动偏好的影响，提出了个人功能区的概念和相关参数来建模和推断用户空间活动偏好。为了在LBSNs中利用稀疏的用户活动数据对用户的时间活动偏好进行建模，我们提出利用不同用户之间的时间活动相似性，并应用非负张量因子分解来协同推断时间活动偏好。最后，我们提出了一个上下文感知的融合框架，结合联合收割机的空间和时间的活动偏好模型的偏好推理。我们评估我们提出的方法从纽约和东京收集的三个真实世界的数据集，并表明我们的STAP模型始终优于基线方法在各种设置。
With the recent surge of location based social networks (LBSNs), activity data of millions of users has become attainable. This data contains not only spatial and temporal stamps of user activity, but also its semantic information. LBSNs can help to understand mobile users' spatial temporal activity preference (STAP), which can enable a wide range of ubiquitous applications, such as personalized context-aware location recommendation and group-oriented advertisement. However, modeling such user-specific STAP needs to tackle high-dimensional data, i.e., user-location-time-activity quadruples, which is complicated and usually suffers from a data sparsity problem. In order to address this problem, we propose a STAP model. It first models the spatial and temporal activity preference separately, and then uses a principle way to combine them for preference inference. In order to characterize the impact of spatial features on user activity preference, we propose the notion of personal functional region and related parameters to model and infer user spatial activity preference. In order to model the user temporal activity preference with sparse user activity data in LBSNs, we propose to exploit the temporal activity similarity among different users and apply nonnegative tensor factorization to collaboratively infer temporal activity preference. Finally, we put forward a context-aware fusion framework to combine the spatial and temporal activity preference models for preference inference. We evaluate our proposed approach on three real-world datasets collected from New York and Tokyo, and show that our STAP model consistently outperforms the baseline approaches in various settings.