Context has been recognized as an important factor to consider in personalized recommender systems. Particularly in location-based services (LBSs), a fundamental task is to recommend to a mobile user where he/she could be interested to visit next at the right time. Additionally, location-based social networks (LBSNs) allow users to share location-embedded information with friends who often co-occur in the same or nearby points-of-interest (POIs) or share similar POI visiting histories, due to the social homophily theory and Tobler’s first law of geography. So, both the time information and LBSN friendship relations should be utilized for POI recommendation.
Tensor completion has recently gained some attention in time-aware recommender systems. The problem decomposes a user-item-time tensor into low-rank embedding matrices of users, items and times using its observed entries, so that the underlying low-rank subspace structure can be tracked to fill the missing entries for time-aware recommendation. However, these tensor completion methods ignore the social-spatial context information available in LBSNs, which is important for POI recommendation since people tend to share their preferences with their friends, and near things are more related than distant things. In this paper, we utilize the side information of social networks and POI locations to enhance the tensor completion model paradigm for more effective time-aware POI recommendation. Specifically, we propose a regularization loss head based on a novel social Hausdorff distance function to optimize the reconstructed tensor. We also quantify the popularity of different POIs with location entropy to prevent very popular POIs from being over-represented hence suppressing the appearance of other more diverse POIs. To address the sensitivity of negative sampling, we train the model on the whole data by treating all unlabeled entries in the observed tensor as negative, and rewriting the loss function in a smart way to reduce the computational cost. Through extensive experiments on real datasets, we demonstrate the superiority of our model over state-of-the-art tensor completion methods.
more »
« less
Points of Interest (POI): a commentary on the state of the art, challenges, and prospects for the future
In this commentary, we describe the current state of the art of points of interest (POIs) as digital, spatial datasets, both in terms of their quality and affordings, and how they are used across research domains. We argue that good spatial coverage and high-quality POI features — especially POI category and temporality information — are key for creating reliable data. We list challenges in POI geolocation and spatial representation, data fidelity, and POI attributes, and address how these challenges may affect the results of geospatial analyses of the built environment for applications in public health, urban planning, sustainable development, mobility, community studies, and sociology. This commentary is intended to shed more light on the importance of POIs both as standalone spatial datasets and as input to geospatial analyses.
more » « less- Award ID(s):
- 2117771
- NSF-PAR ID:
- 10368464
- Publisher / Repository:
- Springer Science + Business Media
- Date Published:
- Journal Name:
- Computational Urban Science
- Volume:
- 2
- Issue:
- 1
- ISSN:
- 2730-6852
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)The information of building types is highly needed for urban planning and management, especially in high resolution building modeling in which buildings are the basic spatial unit. However, in many parts of the world, this information is still missing. In this paper, we proposed a framework to derive the information of building type using geospatial data, including point-of-interest (POI) data, building footprints, land use polygons, and roads, from Gaode and Baidu Maps. First, we used natural language processing (NLP)-based approaches (i.e., text similarity measurement and topic modeling) to automatically reclassify POI categories into which can be used to directly infer building types. Second, based on the relationship between building footprints and POIs, we identified building types using two indicators of type ratio and area ratio. The proposed framework was tested using over 440,000 building footprints in Beijing, China. Our NLP-based approaches and building type identification methods show overall accuracies of 89.0% and 78.2%, and kappa coefficient of 0.83 and 0.71, respectively. The proposed framework is transferrable to other China cities for deriving the information of building types from web mapping platforms. The data products generated from this study are of great use for quantitative urban studies at the building level.more » « less
-
Abstract Non-pharmacologic interventions (NPIs) promote protective actions to lessen exposure risk to COVID-19 by reducing mobility patterns. However, there is a limited understanding of the underlying mechanisms associated with reducing mobility patterns especially for socially vulnerable populations. The research examines two datasets at a granular scale for five urban locations. Through exploratory analysis of networks, statistics, and spatial clustering, the research extensively investigates the exposure risk reduction after the implementation of NPIs to socially vulnerable populations, specifically lower income and non-white populations. The mobility dataset tracks population movement across ZIP codes for an origin–destination (O–D) network analysis. The population activity dataset uses the visits from census block groups (cbg) to points-of-interest (POIs) for network analysis of population-facilities interactions. The mobility dataset originates from a collaboration with StreetLight Data, a company focusing on transportation analytics, whereas the population activity dataset originates from a collaboration with SafeGraph, a company focusing on POI data. Both datasets indicated that low-income and non-white populations faced higher exposure risk. These findings can assist emergency planners and public health officials in comprehending how different populations are able to implement protective actions and it can inform more equitable and data-driven NPI policies for future epidemics.more » « less
-
more » « less
Recommending a Point of Interest (PoI) or a sequence of PoIs to visit based on user’s preferences and geo-locations has been one of the most popular applications of Location-Based Services (LBS). Variants have also been considered which take other factors into consideration, such as broader (implicit or explicit) semantic constraints as well as the limitations on the length of the trip. In this work, we present an efficient algorithmic solution to a novel query –
PaDOC (Paths with Distance, Origin, and Category constraints) – which combines the generation of a path that (a) can be traversed within a user-specified budget (e.g., limit on distance), (b) starts at one of the user-specified origin locations (e.g., a hotel), and (c) contains PoIs from a user-specified list of PoI categories. We show that the problem of deciding whether such a path exists is an NP-hard problem. Based on a novel indexing structure, we propose two efficient algorithms for approximatePaDOC query processing based on both conservative and progressive distance estimations. We conducted extensive experiments over real, publicly available datasets, demonstrating the benefits of the proposed methodologies over straightforward solutions. -
The main objective of Personalized Tour Recommendation (PTR) is to generate a sequence of point-of-interest (POIs) for a particular tourist, according to the user-specific constraints such as duration time, start and end points, the number of attractions planned to visit, and so on. Previous PTR solutions are based on either heuristics for solving the orienteering problem to maximize a global reward with a specified budget or approaches attempting to learn user visiting preferences and transition patterns with the stochastic process or recurrent neural networks. However, existing learning methodologies rely on historical trips to train the model and use the next visited POI as the supervised signal, which may not fully capture the coherence of preferences and thus recommend similar trips to different users, primarily due to the data sparsity problem and long-tailed distribution of POI popularity. This work presents a novel tour recommendation model by distilling knowledge and supervision signals from the trips in a self-supervised manner. We propose Contrastive Trajectory Learning for Tour Recommendation (CTLTR), which utilizes the intrinsic POI dependencies and traveling intent to discover extra knowledge and augments the sparse data via pre-training auxiliary self-supervised objectives. CTLTR provides a principled way to characterize the inherent data correlations while tackling the implicit feedback and weak supervision problems by learning robust representations applicable for tour planning. We introduce a hierarchical recurrent encoder-decoder to identify tourists’ intentions and use the contrastive loss to discover subsequence semantics and their sequential patterns through maximizing the mutual information. Additionally, we observe that a data augmentation step as the preliminary of contrastive learning can solve the overfitting issue resulting from data sparsity. We conduct extensive experiments on a range of real-world datasets and demonstrate that our model can significantly improve the recommendation performance over the state-of-the-art baselines in terms of both recommendation accuracy and visiting orders.more » « less
