Point-of-interest Recommendation Research Articles

A content-location-aware personalized POI recommendation model

Aiming at the data sparsity problem of user-POI matrix in point of interest (POI) recommendation, the more and more studies have explored the contextual factors such as geographical location, content information and social relations to deal with the above-mentioned problem. However, the current research lacks comprehensive analysis and utilization of the relations of these contextual factors. Therefore, we propose a content-location-aware topic model (CLATM) to simulate the user check-in behavior in the decision-making process from the dual-perspective of content and location by using the probability generation method. CLATM consists of two core modules: content topic modeling and location topic modeling. The user check-in content depends on the content topic and location topic. The content topic and location topic jointly determine the user check-in location to a certain extent. The geographic location depends on the location topic and obeys Gaussian distribution. The CLATM model not only properly integrates the important contextual factors such as content, location and geography, but also makes full use of the latent relations between these factors to alleviate the data sparsity effectively. The performance of CLATM model is evaluated on two real location-based social network (LBSN) datasets, Foursquare and Yelp. The experimental results show that the model is superior to the baselines in recall and normalize discounted cumulative gain (NDCG), with the maximum increase of about 141.09% and 94.44% in recall@20 and NDCG@20, respectively. It can be concluded that comprehensive use of the relations of contextual factors can effectively improve the POI recommendation performance.

Context-Enhanced Probabilistic Diffusion for Urban Point-of-Interest Recommendation

Point-of-interest (POI) recommendation has a wide range of application values in smart city services computing. However, extreme sparsity of user-POI matrix seriously affects the recommendation accuracy. Rich contextual information is often utilized to solve data sparsity, whereas how to efficiently integrate them becomes another challenge. To this end, we merge the contextual information into probabilistic diffusion process to propose a novel approach, namely context-enhanced probabilistic diffusion, to generate satisfying POI recommendations under sparse data environment. First, the check-in data is preprocessed to construct the relevant scores that can reflect the relevant degrees between users and POIs expressly. Then, we extract social explicit and implicit trusts from user relationships, and integrate them with time influence to present a time-enhanced social diffusion process to obtain time-social probabilistic score. Next, by merging time factor into geographical distance, a time-enhanced geographical diffusion process is executed to generate time-geographical probabilistic score. Furthermore, we present a context-aware probabilistic matrix factorization to predict the relevant score for a target user on each POI. Finally, unchecked-in POIs with highest predicted relevant scores are recommended for the target user. Experiments executed on real-world datasets suggest that, the proposed approach outperforms the state-of-the-art approaches in terms of the recommendation accuracy.

A top-k POI recommendation approach based on LBSN and multi-graph fusion

POI(Point of Interest) recommendation is a basic and on-going issue in LBSN (Location-based Social Network) services. In this paper, a novel POI recommendation approach which is based on LBSN and multi-graph fusion is proposed. First, we take advantages of the graph neural network to construct user-POI interaction graph based on the rating data of users and construct user social graph based on the user social networks. First-order friends and high-order friends will be considered simultaneously in the user social graph. And then, we present a spectral cluster-based algorithm to gain the latent vector of the POI in location space. After this, the graph neural network is used to learn the information above. Lastly, we predict the score based on the aforementioned information and pick out the top-k POIs with the highest scores to form a recommendation list. Extensive experiments conducted on real datasets demonstrated that the method proposed in this paper can effectively generate the embedding vectors of users and POIs, and can achieve high recommendation accuracy as well.

Spatio-Temporal Unequal Interval Correlation-Aware Self-Attention Network for Next POI Recommendation

As the core of location-based social networks (LBSNs), the main task of next point-of-interest (POI) recommendation is to predict the next possible POI through the context information from users’ historical check-in trajectories. It is well known that spatial–temporal contextual information plays an important role in analyzing users check-in behaviors. Moreover, the information between POIs provides a non-trivial correlation for modeling users visiting preferences. Unfortunately, the impact of such correlation information and the spatio–temporal unequal interval information between POIs on user selection of next POI, is rarely considered. Therefore, we propose a spatio-temporal unequal interval correlation-aware self-attention network (STUIC-SAN) model for next POI recommendation. Specifically, we first use the linear regression method to obtain the spatio-temporal unequal interval correlation between any two POIs from users’ check-in sequences. Sequentially, we design a spatio-temporal unequal interval correlation-aware self-attention mechanism, which is able to comprehensively capture users’ personalized spatio-temporal unequal interval correlation preferences by incorporating multiple factors, including POIs information, spatio-temporal unequal interval correlation information between POIs, and the absolute positional information of corresponding POIs. On this basis, we perform next POI recommendation. Finally, we conduct comprehensive performance evaluation using large-scale real-world datasets from two popular location-based social networks, namely, Foursquare and Gowalla. Experimental results on two datasets indicate that the proposed STUIC-SAN outperformed the state-of-the-art next POI recommendation approaches regarding two commonly used evaluation metrics.

Next-point-of-interest recommendation based on joint mining of regularity and randomness

Point-of-interest (POI) recommendation is important in location-based applications and has attracted considerable research interest. Despite the inspiring achievements of POI recommendation in recent years, POI recommendation based on the modeling of sparse spatiotemporal data remains challenging, suffering from heterogeneity, randomness, and complexity. In this paper, we propose a novel method for next-POI recommendation. It consists of long- and short-term modules, which learn users’ complex behavior using heterogeneous check-in data. We assume that users have relatively stable regularities on different feature spaces in the long term and randomness can be observed in the users’ decision in the short term, which is influenced by various contexts. Hence, in the long-term module, we design a parallel gated recurrent unit (GRU) network to capture the regularities in the time-space, date-space, geo-space, and activity-space separately from the long trajectory history. In the short-term module, we utilize an attention-based multi-context GRU network to capture the context-aware randomness from the recent trajectory. Furthermore, we integrate the long-term regularity and short-term randomness to model the complex mechanism of human mobility and use the hybrid preference to recommend the next POI. We verify the effectiveness of our model on three public check-in datasets, and experimental results indicate that our approach outperforms state-of-the-art methods for POI recommendation.

Pre-training local and non-local geographical influences with contrastive learning

Geographical influences fundamentally help to improve the performance of location-based services (LBS). However, existing LBS approaches rely on abundant task-specific labeled data in an end-to-end manner, which often causes overfitting and sparsity problems. One effective way is to pre-train contextualized representations on unlabeled data with self-supervision to capture intrinsic correlations between locations and their contexts. In this paper, we propose a novel local and non-local geographic representation (LNGR) model with contrastive self-supervised learning, which is able to simultaneously incorporate geospatial proximity as a local geographical influence and relative distance differences as a non-local geographical influence. To capture the inherent dependency between the geographical influences, we pre-train sequential (for non-local) and surrounding (for local) contextual encoders in a unified framework with three different types of self-supervised objectives, hence promoting the quality of contextual point-of-interest (POI) representations. We evaluate our pre-trained model for next POI recommendation on six check-in datasets. The extensive experimental results demonstrate that the superiority of LNGR over existing pre-training and end-to-end recommendation methods. Besides, we further show the effective robustness and generalization ability of our pre-trained model when task-specific labeled data is scarce.

A POI Recommendation Algorithm Based on the Heterogeneous Graph Convolution Network

Point-of-interest (POI) recommendation is a type of recommendation task, which generates a list of places that users may be interested in. There is a complex heterogeneous graph structure between users and points of interest. The current recommendation algorithms are generally based on Euclidean space data, and the algorithms based on graph structure also generally use homogeneous graph convolution. To solve these problems, the author proposes a heterogeneous graph convolution network algorithm based on hierarchical subgraphs (HGCNR). By constructing user-centered subgraph layers and interest point-cantered subgraph layers, respectively, the author performs heterogeneous graph convolution on different subgraphs to obtain more effective user node information and interest point node information and form recommendation result. Experiments on two public data sets show that HGCNR can effectively improve the recommendation performance of interest points and achieve better recommendation results.

POI recommendation with queuing time and user interest awareness

Point-of-interest (POI) recommendation is a challenging problem due to different contextual information and a wide variety of human mobility patterns. Prior studies focus on recommendation that considers user travel spatiotemporal and sequential patterns behaviours. These studies do not pay attention to user personal interests, which is a significant factor for POI recommendation. Besides user interests, queuing time also plays a significant role in affecting user mobility behaviour, e.g., having to queue a long time to enter a POI might reduce visitor’s enjoyment. Recently, attention-based recurrent neural networks-based approaches show promising performance in the next POI recommendation task. However, they are limited to single head attention, which can have difficulty in finding the appropriate user mobility behaviours considering complex relationships among POI spatial distances, POI check-in time, user interests and POI queuing times. In this research work, we are the first to consider queuing time and user interest awareness factors for next POI recommendation. We demonstrate how it is non-trivial to recommend a next POI and simultaneously predict its queuing time. To solve this problem, we propose a multi-task, multi-head attention transformer model called TLR-M_UI. The model recommends the next POIs to the target users and predicts queuing time to access the POIs simultaneously by considering user mobility behaviours. The proposed model utilises POIs description-based user personal interest that can also solve the new categorical POI cold start problem. Extensive experiments on six real-world datasets show that the proposed models outperform the state-of-the-art baseline approaches in terms of precision, recall, and F1-score evaluation metrics. The model also predicts and minimizes the queuing time. For the reproducibility of the proposed model, we have publicly shared our implementation code at GitHub (https://github.com/sajalhalder/TLR-M_UI).

A points of interest recommendation framework based on effective representation of heterogeneous nodes in the Internet of Things

Location-based social networks are a special kind of the Internet of Things in which users and points of interest (POIs) are heterogeneous network nodes. When matching POIs for users, traditional recommendation methods either map users to POI space or map POIs to user space. This direct mapping of the heterogeneous space introduces some noise to the node representation. The sparse interaction between users and POIs makes it difficult to effectively distinguish the representations of similar heterogeneous nodes. Based on the above problems, this paper proposes a recommendation framework that projects heterogeneous network nodes: users and POIs into a unified representation space. Obtain the matching results of nodes in the new problem space and effectively solve the problem of unified representation of heterogeneous nodes in the Internet of Things. The setting of the intermediate latent space can distinguish the representations of similar behavior nodes as much as possible and obtain more accurate recommendation results. We conduct extensive experiments on a four real-world datasets which show that framework has superior performance compared to the state-of-the-art framework for POI recommendation.

Maximizing the influence of bichromatic reverse k nearest neighbors in geo-social networks

Geo-social networks offer opportunities for the marketing and promotion of geo-located services. In this setting, we explore a new problem, called Maximizing the Influence of Bichromatic Reverse k Nearest Neighbors (MaxInfBRkNN). The objective is to find a set of points of interest (POIs), which are geo-textually and socially relevant to social influencers who are expected to largely promote the POIs online. In other words, the problem aims to detect an optimal set of POIs with the largest word-of-mouth (WOM) marketing potential. This functionality is useful in various real-life applications, including social advertising, location-based viral marketing, and personalized POI recommendation. However, solving MaxInfBRkNN with theoretical guarantees is challenging because of the prohibitive overheads on BRkNN retrieval in geo-social networks, and the NP and #P-hardness of finding the optimal POI set. To achieve practical solutions, we present a framework with carefully designed indexes, efficient batch BRkNN processing algorithms, and alternative POI selection policies that support both approximate and heuristic solutions. Extensive experiments on real and synthetic datasets demonstrate the good performance of our proposed methods.

Building and exploiting spatial–temporal knowledge graph for next POI recommendation

Next Point-of-Interest (POI) recommendation has shown great value for both users and businesses in the field of location-based services. Many spatial–temporal inferring methods have been developed to perform this task, but the data sparsity of POI trajectories greatly hinders the recommendation performance. Knowledge graphs (KGs) have been demonstrated as an effective way to tackle data sparsity in the general recommendation field by leveraging the valuable information of entities and relations. Yet, few studies have explored applying KGs for the next POI recommendation task because of the following challenges: (1) how to represent the dynamic mobility behaviors of users with the static entities and relations in KGs; and (2) how to utilize the different types of entities and relations in KGs to capture long- and short-term preferences of users. In this work, we investigate building a spatial–temporal KG (STKG) from check-in sequences of users to promote the next POI recommendation, without introducing any external attributes of users and POIs. In STKG, we design a novel spatial–temporal transfer relation to intuitively capture users’ transition patterns between neighboring POIs. Then, based on the STKG, we propose an innovative model, named STKGRec, for the next POI recommendation, which explicitly models long- and short-term preferences of users in an end-to-end manner. In particular, STKGRec learns both the spatial–temporal correlation of consecutive and nonconsecutive visits in the current check-in sequence to comprehensively capture the short-term preferences of users. Extensive experiments on four real-world datasets demonstrate the superiority of STKGRec against the state-of-the-art baseline methods. The code of our proposed model is available athttps://github.com/WeiChen3690/STKGRec.

ITourSPOT: a context-aware framework for next POI recommendation in location-based social networks

ABSTRACT The rising prosperity of Location-based Social Networks (LBSNs) witnessed an explosion in the availability of geo-tagged social media data, which enables tremendous location-aware online services, especially next point of interest (POI) recommendation. However, previous next POI recommendation studies usually adopt fix-length time windows for user check-in sequence modeling, leading to a limited capacity in capturing fine-grained user temporal preferences that easily change over time. Besides, existing methods often directly leverage multi-modal contexts as auxiliary to alleviate the data sparsity issue, which fails to fully exploit the sequential patterns of contextual information for inferring user interest drift. To address the above challenges, we propose a novel framework named iTourSPOT which extends traditional collaborative filtering methods with a context-aware POI embedding architecture. For enhancing temporal interests modeling capacity, we associate the context feature extraction with varying-length sessions and incorporate check-in frequencies of POIs as prior knowledge to instruct the session representation learning of our model. Moreover, a collaborative sequence transduction model is designed for joint context sequence modeling and session-based POI recommendation. Experimental results on a real-world geo-tagged photo dataset clearly demonstrate the effectiveness of the proposed framework when compared with state-of-the-art baseline methods, especially in both sparse and cold-start scenarios.

An effective points of interest recommendation approach based on embedded meta‐path of spatiotemporal data

AbstractWith the development of mobile networks and the rapid prevalence of location‐based social networks (LBSN), a massive volume of spatiotemporal data has been generated, which is valuable for points of interest (POI) recommendation. However, current studies have not unleashed the full power of such spatiotemporal data, which either explore only a single dimension of the data or consider multiple factors in an asynchronous fashion. In this article, we propose a novel spatiotemporal network‐based recommender framework (STNBR) to effectively recommend POIs for users. Specifically, we first establish a comprehensive conceptual model of spatiotemporal data, involving various essential factors for POIs recommendation. On top of the conceptual model, we design a series of meaningful meta‐paths that simultaneously consider the time and location factors to precisely capture the semantics of user behaviours. By profiling users based on their embedded meta‐paths, our approach can yield meaningful POIs recommendations. We have evaluated our proposal using a realistic dataset obtained from Foursquare and Gowalla, the results of which show that our STNBR model outperforms existing approaches.

POI Recommendation Method of Neural Matrix Factorization Integrating Auxiliary Attribute Information

Point-of-interest (POI) recommendation is the prevalent personalized service in location-based social networks (LBSNs). A single use of matrix factorization (MF) or deep neural networks cannot effectively capture the complex structure of user–POI interactions. In addition, to alleviate the data-sparsity problem, current methods primarily introduce the auxiliary information of users and POIs. Auxiliary information is often judged to be equally valued, which will dissipate some of the valuable information. Hence, we propose a novel POI recommendation method fusing auxiliary attribute information based on the neural matrix factorization, integrating the convolutional neural network and attention mechanism (NueMF-CAA). First, the k-means and term frequency–inverse document frequency (TF-IDF) algorithms are used to mine the auxiliary attribute information of users and POIs from user check-in data to alleviate the data-sparsity problem. A convolutional neural network and an attention mechanism are applied to learn the expression of auxiliary attribute information and distinguish the importance of auxiliary attribute information, respectively. Then, the auxiliary attribute information feature vectors of users and POIs are concatenated with their respective latent feature vectors to obtain the complete latent feature vectors of users and POIs. Meanwhile, generalized matrix factorization (GMF) and multilayer perceptron (MLP) are used to learn the linear and nonlinear interactions between users and POIs, respectively, and the last hidden layer is connected to integrate the two parts to alleviate the implicit feedback problem and make the recommendation results more interpretable. Experiments on two real-world datasets, the Foursquare dataset and the Weibo dataset, demonstrate that the proposed method significantly improves the evaluation metrics—hit ratio (HR) and normalized discounted cumulative gain (NDCG).

Multi-Graph Convolutional Network for Fine-Grained and Personalized POI Recommendation

With the advent of the era of rapid information expansion, the massive data backlog that exists on the Internet has led to a serious information overload problem, which makes recommendation systems a crucial part of human life. In particular, the Point-Of-Interest (POI) recommendation system has been applied to many real-life scenarios, such as life services and autonomous driving. Specifically, the goal of POI recommendation is to recommend locations that match their personalized preferences to users. In existing POI recommendation methods, people tend to pay more attention to the impact of temporal and spatial factors of POI on users, which will alleviate the problems of data sparsity and cold start in POI recommendation. However, this tends to ignore the differences among individual users, and considering only temporal and spatial attributes does not support fine-grained POI recommendations. To solve this problem, we propose a new Fine-grained POI Recommendation With Multi-Graph Convolutional Network (FP-MGCN). This model focuses on the content representation of POIs, captures users’ personalized preferences using semantic information from user comments, and learns fine-grained representations of users and POIs through the relationships between content–content, content–POI, and POI–user. FP-MGCN employs multiple embedded propagation layers and adopts information propagation mechanisms to model the higher-order connections of different POI-related relations for enhanced representation. Fine-grained POI is finally recommended to users through the three types of propagation we designed: content–content information propagation, content–POI information propagation, and POI–user information propagation. We have conducted detailed experiments on two datasets, and the results show that FP-MGCN has advanced performance and can alleviate the data sparsity problem in POI recommendation tasks.

URPI-GRU: An approach of next POI recommendation based on user relationship and preference information

Next POI (Point of Interest) recommendation aims to recommend next POI for users at specific time given users’ historical check-ins. User relationship and preference information are important factors that can affect the user’s decision-making behavior on the next POI. To this end, we propose an approach for the next POI recommendation based on user relationship and preference information, called URPI-GRU (User relationship and Preference information Gated Recurrent Unit). URPI-GRU contains two modules, short-term module and long-term module. First, we construct a user relationship graph and learn user relationship vectors. And then we divide the check-ins into current preference, periodic preference and long-term preference according to the user’s check-in time. In the short-term module, the user’s periodic preference and current preference are learned through the GRU model, and they are concatenated with the user relationship vector to learn the short-term scores of POIs. In the long-term module, the user’s long-term preference is mined through the K-nearest neighbor sequences to obtain the long-term scores of the POIs. Last, we recommend the POIs based on the total score of short-term and long-term scores. Extensive experiments on two representative real-world datasets demonstrated that our model yields significant improvements over the state-of-the-art methods.

POIs Category Recommendation for Cultural Country Travel Enterprises Based on Check-In Information

With the ever-increasing popularity of traveling markets, more people are willing to spend their time and enjoy life by visiting some points of interest (POI) especially for the citizens living in cities. Therefore, it is of practical and significant value for travel enterprises to recommend appropriate country POIs to target travelers. However, the massive POIs as well as their diversity place a heavy burden on the POIs recommendation decision making especially when the available historical traveler-POIs check-in data are very sparse. In view of this challenge, the authors put forward a novel cultural country POIs category recommendation method based on historical knowledge and experienced information (e.g., check-in time and POIs category, i.e., CPCR). At last, CPCR method is evaluated via experiments on WS-DREAM dataset.

An ensemble learning model for preference-geographical aware point-of interest recommendation

An ensemble learning model for preference-geographical aware point-of interest recommendation

Using Attributes Explicitly Reflecting User Preference in a Self-Attention Network for Next POI Recommendation

With the popularity of location-based social networks such as Weibo and Twitter, there are many records of points of interest (POIs) showing when and where people have visited certain locations. From these records, next POI recommendation suggests the next POI that a target user might want to visit based on their check-in history and current spatio-temporal context. Current next POI recommendation methods mainly apply different deep learning models to capture user preferences by learning the nonlinear relations between POIs and user preference and pay little attention to mining or using the information that explicitly reflects user preference. In contrast, this paper proposes to utilize data that explicitly reflect user preference and include these data in a deep learning-based process to better capture user preference. Based on the self-attention network, this paper utilizes the attributes of the month of the check-ins and the categories of check-ins during this time, which indicate the periodicity of the user’s work and life and can reflect the habits of users. Moreover, considering that distance has a significant impact on a user’s decision of whether to visit a POI, we used a filter to remove candidate POIs that were more than a certain distance away when recommending the next POIs. We use check-in data from New York City (NYC) and Tokyo (TKY) as datasets, and experiments show that these improvements improve the recommended performance of the next POI. Compared with the state-of-the-art methods, the proposed method improved the recall rate by 7.32% on average.

Graph-Enhanced Spatial-Temporal Network for Next POI Recommendation

The task of next Point-of-Interest (POI) recommendation aims at recommending a list of POIs for a user to visit at the next timestamp based on his/her previous interactions, which is valuable for both location-based service providers and users. Recent state-of-the-art studies mainly employ recurrent neural network (RNN) based methods to model user check-in behaviors according to user’s historical check-in sequences. However, most of the existing RNN-based methods merely capture geographical influences depending on physical distance or successive relation among POIs. They are insufficient to capture the high-order complex geographical influences among POI networks, which are essential for estimating user preferences. To address this limitation, we propose a novel Graph-based Spatial Dependency modeling (GSD) module, which focuses on explicitly modeling complex geographical influences by leveraging graph embedding. GSD captures two types of geographical influences, i.e., distance-based and transition-based influences from designed POI semantic graphs. Additionally, we propose a novel Graph-enhanced Spatial-Temporal network (GSTN), which incorporates user spatial and temporal dependencies for next POI recommendation. Specifically, GSTN consists of a Long Short-Term Memory (LSTM) network for user-specific temporal dependencies modeling and GSD for user spatial dependencies learning. Finally, we evaluate the proposed model using three real-world datasets. Extensive experiments demonstrate the effectiveness of GSD in capturing various geographical influences and the improvement of GSTN over state-of-the-art methods.