Point Of Interest Recommendation Model Research Articles

Where To Go at the Next Timestamp

The next Point of Interest (POI) recommendation is the core technology of smart city. Current state-of-the-art models attempt to improve the accuracy of the next POI recommendation by incorporating temporal and spatial intervals or by partitioning the POI coordinates into grids. However, they all overlook a detail that in real life, people always want to know where to go at an exact time point or after a specific time interval instead of aimlessly asking where to go next. Moreover, due to individual preferences, different users may visit different places at the same timestamp. Therefore, utilizing timestamp queries can enhance the personalized recommendation capability of the model and mitigate overfitting risks. These implies that using timestamp can achieve more precise recommendations. To the best of our knowledge, we are the first to use the next timestamp for next POI recommendation. In particular, we propose a Time-Stamp Cross Attention Network (TSCAN). TSCAN is a two-layer cross-attention network. The first layer, Time Stamp Cross Attention Block (TSCAB), uses cross-attention between the next timestamp and historical timestamps, and multiplies the attention scores on corresponding POI to predict the next POI that is most related to the history. The other layer, Cross Time Interval Aware Block (CTIAB), applies the time intervals between the next timestamp and historical timestamps to the POI obtained by TSCAB and historical POIs, allowing temporally adjacent POIs to have a greater similarity. Our model not only has a significant improvement in accuracy but also achieves the goal of personalized recommendation, effectively alleviating overfitting. We evaluate the proposed model with three real-world LBSN datasets, and show that TSCAN outperforms the state-of-the-art next POI recommendation models by 5~9%. TSCAN can not only recommend the next POI, but also recommend the possible POI to visit at any specific timestamp in the future.

MCGCL: A multi-contextual graph contrastive learning-based approach for POI recommendation

<abstract> <p>This paper focused on the point-of-interest (POI) recommendation task. Recently, graph representation learning-based POI recommendation models have gained significant attention due to the powerful modeling capacity of graph structural data. Despite their effectiveness, we have found that recent methods struggle to effectively utilize information from POIs that have not been checked in, which could limit their performance. Hence, in this paper, we proposed a new model, named the multi-contextual graph contrastive learning (MCGCL) model, which introduces the contrastive learning into graph representation learning-based methods. First, MCGCL extracts interactions between POIs under different contextual factors from user check-in records using predefined graph structure information. Next, it samples important POI sets from different contextual factors using a random walk-based method. Then, it introduces a new contrastive learning loss that incorporates contextual information into traditional contrastive learning to enhance its ability to capture contextual information. Finally, MCGCL employs a graph neural network (GNN) model to learn representations of users and POIs. Extensive experiments on real-world datasets have demonstrated the effectiveness of MCGCL on the POI recommendation task compared to representative POI recommendation approaches.</p> </abstract>

Exploiting User Mobility for Time-aware POI Recommendation in Social Networks

Location-Based Social Networks (LBSNs) have recently gained increasing popularity. Timeaware Point-of-Interest(POI) recommendation is one of the most important location-aware services, which can recommend locations to a target user at the specific time based on check-in history. However, current techniques ignore user’s mobility within a region, which plays a vital role in the POI chosen decision. Most of existing algorithms fail to capture the latent relations behind the temporal factors and geographical influence. In this paper, we propose a novel hybrid Time-aware POI Recommendation model based on User Mobility: TPR-UM, which improves the POI recommendation accuracy greatly. More specifically, by introducing the implicit region factor, we capture users’ mobility through collective user actions and geographical properties of locations. We generate the check-in patterns based on different time intervals and different regions to exploit the latent relations between temporal factors and geographical influence. Finally, we conduct comprehensive experiments on two real-world datasets, Gowalla and Foursquare. The experimental results demonstrate that our hybrid method is effective and outperforms other state-of-the-art algorithms in terms of precision, recall and Fβ measurement.

A BiLSTM-attention-based point-of-interest recommendation algorithm

Abstract Aiming at the problem that users’ check-in interest preferences in social networks have complex time dependences, which leads to inaccurate point-of-interest (POI) recommendations, a location-based POI recommendation model using deep learning for social network big data is proposed. First, the original data are fed into an embedding layer of the model for dense vector representation and to obtain the user’s check-in sequence (UCS) and space-time interval information. Then, the UCS and spatiotemporal interval information are sent into a bidirectional long-term memory model for detailed analysis, where the UCS and location sequence representation are updated using a self-attention mechanism. Finally, candidate POIs are compared with the user’s preferences, and a POI sequence with three consecutive recommended locations is generated. The experimental analysis shows that the model performs best when the Huber loss function is used and the number of training iterations is set to 200. In the Foursquare dataset, Recall@20 and NDCG@20 reach 0.418 and 0.143, and in the Gowalla dataset, the corresponding values are 0.387 and 0.148.

POI recommendation for occasional groups Based on hybrid graph neural networks

Recently, POI (Point-of-interest) recommendation for groups has become a critical challenge when helping groups to discover potentially interesting new places, and some effective recommendation models have been proposed to address this issue. However, most existing research focuses on POI recommendation for fixed groups, few studies have been conducted on POI recommendation for occasional groups. To tackle this issue, we propose a POI recommendation model for occasional groups based on Hybrid Graph Neural Networks (termed as PROG-HGNN) which combines excellent graph neural networks models. Firstly, PROG-HGNN generates the fitted representation of the occasional group based on the Node Influence Indicator (INF) method and Graph Attention Networks (GAT) model. Then, PROG-HGNN learns POIs’ representations containing members’ POI interaction preferences and members’ POI transfer preferences with the Signed Bipartite Graph Neural Networks (SBGNN) model and the Session-based Graph Neural Networks (SRGNN) model, respectively. Finally, PROG-HGNN recommends the potential POIs for the occasional group based on the fitted representation of the occasional group and the learned representations of POIs. We verify our proposed model on three public benchmark datasets (Foursquare, Gowalla and Yelp), which contains 124,933 to 860,888 POI check-in records. The comparison between our proposed model and the twelve baseline models demonstrates the outstanding performance of PROG-HGNN. In terms of Precision@K and Recall@K, our model achieves about 32.92% and 19.67% improvement compared with the best baseline models on the three benchmark datasets averagely. Adequate ablation experiments prove the effectiveness of the members’ POI interaction preferences learning module and POI transfer preferences learning module.

Feature-based POI grouping with transformer for next point of interest recommendation

With the increasing prevalence of location-based services, Point of Interest (POI) recommendation has become an active research topic. While Graph Neural Networks (GNNs) have been widely used in POI recommendation models, they suffer from computational efficiency limitations when the graph structure is large. In this paper, we propose a new next POI recommendation model, which is backboned by a lightweight, feature-based POI grouping (FPG) method and a Transformer network. A unique feature of the proposed model is it uses the FPG method, which divides POIs into multiple groups based on their geographical and popularity features and analyze the similarity among the users’ preferences on the groups. By using the FPG method rather than graph-based structures, the proposed model largely reduces the computational cost in making next POI recommendation. The POI embeddings generated by the FPG method are then fed into a Transformer to generate the recommendation result. We test the proposed model on three real-world datasets and conduct comprehensive comparison studies to validate the performance of the model. The experiment results show that the proposed model has superior computational efficiency while preserving sufficient next POI recommendation accuracy. Key findings and critical implications from the experiment result and the mechanistic design of the model are also discussed in detail.

Capacity-aware fair POI recommendation combining transformer neural networks and resource allocation policy

Point of Interest (POI) recommendations have primarily focused on maximising user satisfaction, while neglecting the needs of POIs and their operators. One such need is recommendation exposure, which can lead to envy among the POIs. Some POIs may be under-recommended, while others may be over-recommended, resulting in dissatisfaction for both staff and users due to long queues or overcrowding. Existing work has not addressed the trade-off between satisfying user preferences and being fair to POIs, which typically aim to operate at capacity. Therefore, we introduce the POI fair allocation problem to model this issue, taking into account both user satisfaction and POI exposure fairness. To address this problem, we propose a fair POI allocation technique that balances user satisfaction and POI capacity-based exposure simultaneously. Our proposed model utilises existing (transformer neural networks and attention LSTM model) personalised POI recommendation models that capture users’ spatio-temporal influences and interests in POI visits. We then propose POI capacity-based allocation using the over-demand cut policy and under-demand add policy, which ensures POI exposure ratio and envy-freeness up to certain thresholds. We evaluate the performance of our proposed model on five datasets containing real-life POI visits. Experimental evaluations show that our proposed model outperforms baselines in terms of user and POI-based evaluation metrics. To ensure reproducibility, we have publicly shared our source code at Codeocean.

POI Recommendation Model Using Multi-Head Attention in Location-Based Social Network Big Data

A point of interest (POI) recommendation model using deep learning in location-based social network big data is proposed. Firstly, the features of POI are divided into inherent features composed of attributes such as geographical location and category, and semantic features of relevance composed of spontaneous access by users. Secondly, the inherent attribute features and semantic features of POI are extracted by constraint matrix decomposition and word vector model respectively, and the two hidden vectors are spliced into the feature vectors of POI to solve the problems of data sparsity and cold start. Finally, the multi-head attention is used to obtain the key information of user preferences, and a deep learning recommendation framework is constructed to model the nonlinear interaction between features. Experiments show that when the recommendation list is 10, the precision and recall of the proposed method are 0.118 and 0.135 respectively, which are better than the comparative recommendation method.

Intelligent Sensors for POI Recommendation Model Using Deep Learning in Location-Based Social Network Big Data

Aiming at the problem that the existing Point of Interest (POI) recommendation model in social network big data is difficult to extract deep feature information, a POI recommendation model based on deep learning in social networks and big data is proposed in this article. The input data are all gathered through intelligent sensors to apply some raw data pre-processing tasks and thus reduce the computational burden on the model. First, a POI static feature extraction method based on symmetric matrix decomposition is designed to capture the geographical location and POI category features in Location-Based Social Networking (LBSN). Second, the improved Continuous Bags-of-Words (CBOW) model is used to extract the semantic features in the user comment information, and realize the implicit vector representation of POI in geographic, category, semantic and temporal feature space. Finally, by adaptively selecting relevant check-in activities from the check-in history to learn and change user preferences, the Geographical-Spatiotemporal Gated Recurrent Unit Network (GSGRUN) can distinguish the user preferences of different check-in. Experiments show that when the length of the recommendation list is 15, the precision of the proposed algorithm on the loc-Gowalla data set is 0.0686, the recall is 0.0769, and the precision on the loc-Brightkite data set is 0.0659, the recall is 0.0835, both of which are better than the comparative recommendation methods. Therefore, compared with the comparison methods, the proposed method can significantly improve the performance of the POI recommendation system.

A matrix factorization recommendation model for tourism points of interest based on interest shift and differential privacy

Adding noise to user history data helps to protect user privacy in recommendation systems but affects the recommendation performance. To solve this problem, a matrix factorization tourism point of interest recommendation model based on interest offset and differential privacy is proposed in this paper. The recommendation performance of the model is improved by analyzing user interest preferences. Specifically, user interest offsets are extracted from user tags and user ratings under time-series factors to calculate user interest drift. Then, similar neighbors are found to train user feature preferences which are integrated into the matrix model in the form of regular terms. Meanwhile, based on the differential privacy theory, a privacy neighbor selection algorithm combining the K-Medoides clustering algorithm and index mechanism is designed to effectively protect the identity of neighbors and prevent KNN attacks. Besides, the Laplace mechanism is used to implement differential privacy protection for the model’s gradient descent process. Finally, the feasibility of the proposed recommendation model is verified through experiments, and the experimental results indicate that this model has advantages in recommendation accuracy and privacy protection.

An efficient privacy-preserving point-of-interest recommendation model based on local differential privacy

With the rapid development of point-of-interest (POI) recommendation services, how to utilize the multiple types of users’ information safely and effectively for a better recommendation is challenging. To solve the problems of imperfect privacy-preserving mechanism and insufficient response-ability to complex contexts, this paper proposes a hybrid POI recommendation model based on local differential privacy (LDP). Firstly, we introduce randomized response techniques k-RR and RAPPOR to disturb users’ ratings and social relationships, respectively and propose a virtual check-in time generation method to deal with the issue of missing check-in time after disturbance. Secondly, for simultaneously combining multiple types of information, we construct a hybrid model containing three sub-models. Sub-model 1 considers the effect of user preference, social relationship, forgetting feature, and check-in trajectory on similarity calculation. Sub-model 2 analyzes the geographical correlation of POIs. Sub-model 3 focuses on the categories of POIs. Finally, we generate the recommendation results. To test the performance of privacy-preserving and recommendation, we design three groups of experiments on three real-world datasets for comprehensive verifying. The experimental results show that the proposed method outperforms existing methods. Theoretically, our study contributes to the effective and safe usage of multidimensional data science and analytics for privacy-preserving POI recommender system design. Practically, our findings can be used to improve the quality of POI recommendation services.

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.

Https://irojournals.com/aicn/AllVolumes.html

Most of the traditional recommendation algorithm models are recommended based on the user's own historical preferences, although it can recommend POI for users to a certain extent. But in real life, people are more willing to ask their friends what they think when they have a difficult decision. Therefore, a word2vec-based social relationship point of interest recommendation model (W-SimTru) is proposed, which combines the similarity of friends based on cosine similarity with the friend trust recommendation algorithm based on TF-IDF to improve the model recommendation effect. In addition, before modeling the similarity of users, word2vec is used to process the user's historical check-in behavior to solve the problem of inaccurate recommendation due to sparse check-in data. Finally, experiments are carried out on three datasets of Los Angeles, Washington and NYC in Gowalla, and the experimental results show that the proposed W-SimTru recommendation algorithm outperforms the algorithms of the three comparative experiments.

Influence-Aware Successive Point-of-Interest Recommendation

In recent years, with the rapid development of mobile applications, user check-in histories have been increasing. Successive point-of-interest (POI) recommendation has gained growing attention. Existing successive point-of-interest recommendation methods learn long- and short-term user preferences through historical check-in sequences to provide more personalized services. However, due to sparse data and complicated temporal patterns, the application of such technique is still limited by two challenges: 1) difficulty meeting user travel needs in time; 2) difficulty capturing users complicated behavior patterns. To address this problem, we propose a new Influence-Aware successive POI recommendation Model (InfAM), which can learn the influence of POIs in a short-term sequence fragment for next point-of-interest recommendation. To capture periodic patterns of user movements, InfAM takes a user’s check-in data within a day as an input sequence to address the current travel needs of the user. In addition, based on multihead attention mechanism and user embedding, InfAM focuses on the influence of POIs in short-term sequences and general user preferences in these sequences. Therefore, InfAM integrates three specific dependencies, which can fully learn the dynamic interaction between short-term preferences: the influence of POIs in short-term sequence fragments (POI-poi), user preferences (POI-user), and the periodicity of check-ins (POI-time). Evaluation results on real-world datasets show that InfAM achieves state-of-the-art recommendation performance.

Relational POI recommendation model combined with geographic information.

Point of interest (POI) recommendation is a popular personalized location-based service. This paper proposes a Geographic Personal Matrix Factorization (GPMF) model that makes effective use of geographic information from the perspective of the relationship between POIs and users. This model considers the role of geographic information from multiple perspectives based on the locational relationship among users, the distributional relationship between users and POIs, and the proximity and clustering relationship among POIs. The GPMF mines the influence of geographic information on different objects and carries out unique modeling through cosine similarity, non-linear function, and k nearest neighbor (KNN). This study explored the influence of geographic information on POI recommendation through extensive experiments with data from Foursquare. The result shows that GPMF performs better than the commonly used POI recommendation algorithm in terms of both precision and recall. Geographic information through proximity relations effectively improves the recommendation algorithm.

Research of Art Point of Interest Recommendation Algorithm Based on Modified VGG-16 Network

<p>Traditional point of interest (POI) recommendation algorithms ignore the semantic context of comment information. Integrating convolutional neural networks into recommendation systems has become one of the hotspots in art POI recommendation research area. To solve the above problems, this paper proposes a new art POI recommendation model based on improved VGG-16. Based on the original VGG-16, the improved VGG-16 method optimizes the fully connection layer and uses transfer learning to share the weight parameters of each layer in VGG-16 pre-training model for subsequent training. The new model fuses the review information and user check-in information to improve the performance of POI recommendation. Experiments on real check-in data sets show that the proposed model has better recommendation performance than other advanced points of interest recommendation methods.</p> <p> </p>

Exploring an Efficient POI Recommendation Model Based on User Characteristics and Spatial-Temporal Factors

The advent of mobile scenario-based consumption popularizes and gradually maturates the application of point of interest (POI) recommendation services based on geographical location. However, the insufficient fusion of heterogeneous data in the current POI recommendation services leads to poor recommendation quality. In this paper, we propose a novel hybrid POI recommendation model (NHRM) based on user characteristics and spatial-temporal factors to enhance the recommendation effect. The proposed model contains three sub-models. The first model considers user preferences, forgetting characteristics, user influence, and trajectories. The second model studies the impact of the correlation between the locations of POIs and calculates the check-in probability of POI with the two-dimensional kernel density estimation method. The third model analyzes the influence of category of POI. Consequently, the above results were combined and top-K POIs were recommended to target users. The experimental results on Yelp and Meituan data sets showed that the recommendation performance of our method is superior to some other methods, and the problems of cold-start and data sparsity are alleviated to a certain extent.

Leveraging graph neural networks for point-of-interest recommendations

Point-of-Interest (POI) recommendation, i.e., suggesting POIs that a user is likely to visit, is a key task to improve user experience in location based social networks (LBSNs). Existing models either focus on geographical influence without considering other factors such as social influence and temporal influence or rely on linear methods to combine different modeling factors, lacking a sophisticated and systematical way to learn representations for users and POIs for recommendation. To remedy these issues, in this work we propose GNN-POI, a generic POI recommendation framework that leverages Graph Neural Networks (GNNs), which demonstrate powerful modeling capacity to learn node representations from node information and topological structure to improve POI recommendation. Specifically, we construct a LBSN graph comprising of two types of nodes, i.e., user node and POI node. For a target user, her preference representation is learned by combining (1) representations of her social connection nodes and (2) representations of the visited POI nodes. For social connection nodes integration, in order to model the complicated and multifaceted social influence, an attention mechanism is applied to learn strengths of heterogeneous social relations; for location nodes integration, we utilize Bi-directional Long Short-Term Memory (Bi-LSTM) to model users’ sequential check-in behavior, taking into account geographical and temporal features. Extensive experiments conducted over three real LBSN datasets show that the proposed GNN based framework significantly outperforms the state-of-the-art POI recommendation models in terms of precision, recall and Normalized Discounted Cumulative Gain (NDCG).

STPR: A Personalized Next Point-of-Interest Recommendation Model with Spatio-Temporal Effects Based on Purpose Ranking

The problem of personalized next point-of-interest (POI) recommendation is significant and of practical value in location-based social networks (LBSNs). Due to the sparsity of data in regard to check-ins, POI recommendations remain a challenging problem. Previous work developed recommendation models by taking into consideration the properties of user’s mobility, for example, spatio-temporal information and the similarity of movement rules. However, they ignore the influence of trip-purpose on user’s mobility, and the memory effect of historical check-in behavior at the same location. To cope with this problem, a POI recommendation model with <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> patio- <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">T</b> emporal effects based on <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">P</b> urpose <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">R</b> anking (STPR) is proposed. STPR contains two important phases: (1) Purpose prediction: classifying the POIs in the spatio-temporal database into four categories. Each category corresponds to a purpose. Then, a purpose ranking model is constructed to model the selection of user’s intended purpose for the trip. (2) The scoring of each candidate POI: the properties of spatial and temporal information are taken into consideration when calculating the score. For the spatial property, the kernel density estimation is used to estimate the visiting probability of a certain POI. For the temporal property, we focus on the time interval and the POI exploration mechanism. We find that POI exploration mechanism can reflect a user’s mobility of visiting new POIs. Furthermore, a method based on Bayesian personalized ranking, called BPR, is proposed to estimate the time interval for unvisited POIs. Extensive experiments were conducted on two real datasets, and the experimental results demonstrate that the recommendation accuracy of the STPR model outperforms the state-of-the-art POI recommendation models with good runtime performance.

PREFER

Point-of-Interest (POI) recommendation is significant in location-based social networks to help users discover new locations of interest. Previous studies on such recommendation mainly adopted a centralized learning framework where check-in data were uploaded, trained and predicted centrally in the cloud. However, such a framework suffers from privacy risks caused by check-in data exposure and fails to meet real-time recommendation needs when the data volume is huge and communication is blocked in crowded places. In this paper, we propose PREFER, an edge-accelerated federated learning framework for POI recommendation. It decouples the recommendation into two parts. Firstly, to protect privacy, users train local recommendation models and share multi-dimensional user-independent parameters instead of check-in data. Secondly, to improve recommendation efficiency, we aggregate these distributed parameters on edge servers in proximity to users (such as base stations) instead of remote cloud servers. We implement the PREFER prototype and evaluate its performance using two real-world datasets and two POI recommendation models. Extensive experiments demonstrate that PREFER strengthens privacy protection and improves efficiency with little sacrifice to recommendation quality compared to centralized learning. It achieves the best quality and efficiency and is more compatible with increasingly sophisticated POI recommendation models compared to other state-of-the-art privacy-preserving baselines.