A personalized point-of-interest recommendation model via fusion of geo-social information
Introduction
Nowadays, location-based social networks (LBSNs), such as Foursquare and Gowalla, has been growing rapidly, due to the advances in location-acquisition and wireless communication technologies. In LBSNs, users check in some interesting locations and share their travel experiences by uploading photos, providing ratings and comments. Since LBSNs have collected a huge volume of users’ activity records, LBSNs have become an ideal platform to investigate users’ online behavior patterns. Many interesting and valuable applications can be built on this platform, such as location recommender system [1], [2], traveling routes recommendation [3], [4], extracting robust feature of location from remote sensing images [5], [6], and so on. As an important component of LBSNs, POI recommendation first helps users to explore new POIs. Then, it also helps advertising agencies to launch location-aware personalized services for potential customers and improve business profits [7].
Most existing POI recommendation methods [8], [9], [10] apply the collaborative filtering techniques with the user-POI check-in matrix to compute the preference score between a user and an unvisited POI. However, the user-POI check-in matrix is highly sparse with numerous missing entries, because users have only visited a very small proportion of POIs in an LBSN. As a result, these methods usually suffer from low recommendation quality. Since the Netflix-prize competition, the recommendation algorithm based on matrix-factorization (MF) techniques [11] have received extensive attention from academia and industry due to their good scalability and accurate predictive ability to deal with large-scale data. Several sophisticated and highly efficient MF-based models have been proposed. Representative ones of this kind include SVD++ model [12], probabilistic MF model [13], and nonparametric MF model [14].
In recent years, further research on matrix factorization yields more sophisticated models, e.g., LF-based CF model via second-order optimization model [15], weighted trace-norm regularization-based model [16], collaborative Gaussian process-based preference model [17], alternating direction method-based nonnegative latent factor model [18], [19], [20], [21], [22]. Meanwhile, these ideas are also used to address other relative issues. e.g., QoS prediction [23], [24], heavy computational overhead in ELM [25], particle swarm optimization [26], [27], [28], kalman filter extension [29], [30], video re-indexing [31], and mobile-user tracking [32].
Compared with the conventional recommendation systems, POI recommender systems using sparse geo-social networking data are more complex in LBSNs, which have the following unique features:
(1) Geographic influence: in LBSN, POIs are encoded with latitude and longitude, which distinguishes POIs form other items, such as books, music and movies in conventional recommender systems, which is called geographical influence.
(2) Social influence: in LBSNs, a person may prefer POIs highly recommended by her friends. In other word, social friends are tend to share more common interest than strangers, which is called social influence.
Based on the unique characteristics of the POI recommendation system mentioned above, some studies [33], [34] have turn to integrate the geographical influence with users’ social influence in LBSNs to enhance the quality of location recommendations. The social friendships is exploited as a user-user similarity matrix to improve the quality of location recommendation. Unfortunately, these studies suffer from two major limitations.
(1) The majority of existing POI recommendation algorithms have come up with a variety of geographic information modeling systems [35], [36], [37], [38] in light of the First Law of geography. For example, The literatures [35], [36] assume that there is an inverse relationship between a user’ s preference to a POI and the distance from a certain POI to the POI that the user has visited. The literatures [37] assume that the distance of visited locations follows a power-law distribution (PD), while in other document [38] a multi-center Gaussian model is proposed on the basis of the gathering effect in terms of the locations of users’ check-in. In these studies, the geographical influence of locations is universally modeled as a common distance distribution for all users or applied the same inversely proportional relation between the propensity and the distance for all users. But multiple factors (e.g., other users’ past check-in activities and the user’ s own personality etc.) can reveal the real geographical influence of locations on users’ check-in behaviors. For instance, indoorsy persons are inclined to conduct check-in POIs around their houses, while outdoorsy persons are more likely to travel around the world and explore new POIs. We focus on real-world examples who are randomly chosen from Foursquare [39] to show that a user’ s check-in behavior is unique. In Fig. 1, we can observe that the distribution of check-ins of the three users is quite different and extremely personalized.
(2) Currently, in some references [40], [41], [42], [43], the similarities between users are seamlessly connected to the collaborative filtering recommendation models. In general, when computing users’ similarities, such similarity measurement only considers those items or users sharing similar ratings for the purpose of easy calculation, which makes the predicting accuracy of the similarity measurement remains at a low level. Some researchers at present have integrated the users’ degree of trust as one of the most important types of social information into the recommendation systems when trying to improve the recommendation quality and have made certain achievements so far [44], [45], [46], [47], [48], [49]. However, the improvement of most trust social information-based recommender systems still have its inherent limitations, and the explanations are as follows: (1) in LBSNs, the fact is that a user only trusts a few other users, leaving a large number of fuzzy and sparse relationships among users. In other words, the data collected from LBSNs is imbalanced, and the explicit trust relationship between users form a non-linear relationship; (2) given very sparse trust networks exist, most existing works only consider users’ explicit trust relationship value, and ignore many valuable implicit trust relations as well as the characteristics; (3) friends with mutual trust are impossible to have completely similar interests. Therefore, explicit trust relationship may involves too much noise, which consequently impacts the performance of recommender systems.
In this paper, we propose a novel personalized geo-social POI recommendation model, called GeoEISo. The contributions of our work are summarized below:
(1) To fully consider users’ personalized check-in behaviors to model geographic influence, we propose to adopt a kernel function density estimation method with an adaptive bandwidth in different level to model geographic influence, which can obtain different distribution forms according to users’ check-in activities. Actually, to best our knowledge, no previous works investigate the personalized geographical influence of locations on a user’ s check-in behavior through learning different kernel bandwidths when adopting kernel density estimation algorithms.
(2) Incorporating trust social information into recommender systems has demonstrated potential to improve social recommendation performance, we propose a novel trust-based social recommendation model based on SVD++ model, which both the explicit and implicit trust relationship of user and ratings are involved to generate predictions. In addition, to the authors’ knowledge, this is the first work that adopt support vector regression based on the Gaussian radial basis function to model the explicit trust relationship to make sure outstanding learning ability and satisfactory precision, indicating its novelty.
(3) To improve the quality of POI recommendations, we design of decomposition model based on the matrix factorization model in an effort to integrate the social information and geographical information.
(4) We conduct extensive experiments to evaluate the performance of GeoEISo on two large-scale real-world data sets. Experimental results show that GeoEISo outperforms other state-of-the-art POI recommendation algorithms.
The rest of this paper is organized as follows. Section 2 briefly reviews related work in POI recommender systems. Section 3 introduces the preliminary knowledge used in this paper. Section 4 describes the details of our proposed POI recommendation algorithm. Experiments are evaluated in Section 5. Finally, we conclude this paper and present some directions for future work in Section 6.
Section snippets
Related work
In general, existing POI recommendation approaches are classified into three categories: collaborative filtering based POI recommendation, geographic influence enhanced POI recommendation and social information enhanced POI recommendation.
Problem definition and preliminaries
In this section, we first introduce several notations used in the paper and then formally define the problem of POI recommendation. At last, we briefly introduce matrix factorization for POI recommendation.
Geoeiso POI recommendation model
In this section, the proposed POI recommendation GeoEISo will be proposed in details.
Dataset description
We use two dataset [34] to evaluate the proposed approach from Foursquare. Foursquare is one of the most popular online LBSNs. It has more than 20 million users and 2 billion check-ins as of April, 2012. The statistics of the two data sets are shown in Table 1. One dataset is collected from New York (NYC), U.S.A., which contains 47,240 users, 388,594 check-ins, 203,765 locations and 810,672 social links (or called trust). The density of NYC is . The other dataset is collected from Los
Conclusion and future work
Along with the development of mobile devices, GPS and other technologies, LBSNs is becoming more and more popular. As a crucial component of LBSNs, POI recommendation can satisfy users’ personalized needs and alleviate information overload. To solve the problems of traditional POI recommendation algorithms, this paper proposes a novel personalized POI recommendation model based on users’ check-in behaviors with fusion of geo-social information: GeoEISo. GeoEISo model is designed to offer
Acknowledgments
This work is supported by National Basic Research Program of China (2012CB719905), National Natural Science Foundation of China (41201404) and Fundamental Research Funds for the Central Universities of China (2042015gf0009).
Rong Gao received the M.S. degree in Computer Science in 2007 from Hubei University, Wuhan, China. He is currently pursuing the Ph.D. degree for Computer Science in Computer School, Wuhan University, China. His research interests include data mining and intelligent recommendation.
References (90)
- et al.
A personal route prediction system based on trajectory data mining
Inf. Sci.
(2011) - et al.
Target detection based on a dynamic subspace
Pattern Recogn.
(2014) - et al.
A switching delayed PSO optimized extreme learning machine for short-term load forecasting
Neurocomputing
(2017) - et al.
Core: Exploiting the personalized influence of two-dimensional geographic coordinates for location recommendations
Inf. Sci.
(2015) - et al.
A mobile 3d-GIS hybrid recommender system for tourism
Inf. Sci.
(2012) - et al.
Localized support vector regression for time series prediction
Neurocomputing
(2009) - et al.
Stellar: spatial-temporal latent ranking for successive point-of-interest recommendation
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence
(2016) - et al.
Unified point-of-interest recommendation with temporal interval assessment
Proceedings of the Twenty-second ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
(2016) - et al.
Learning travel recommendations from user-generated GPS traces
ACM Trans. Intell. Syst. Technol.
(2011) - et al.
A discriminative metric learning based anomaly detection method
IEEE Trans. Geosci. Remote Sens.
(2014)
Inferring a personalized next point-of-interest recommendation model with latent behavior patterns
Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence
CLR: a collaborative location recommendation framework based on co-clustering
Proceedings of the Thirty-fourth International ACM SIGIR Conference on Research and Development in Information Retrieval
Lars: A location-aware recommender system
Proceedings of the Twenty-eighth IEEE International Conference on Data Engineering
Towards mobile intelligence: learning from GPS history data for collaborative recommendation
Artif. Intell.
Matrix factorization techniques for recommender systems
Computer
Factorization meets the neighborhood: a multifaceted collaborative filtering model
Proceedings of the Fourteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Probabilistic matrix factorization
Proceedings of the Twenty-fourth International Conference on Machine Learning
Algorithms for non-negative matrix factorization
Proceedings of the Fourteenth Annual Conference on Neural Information Processing Systems
An efficient second-order approach to factorize sparse matrices in recommender systems
IEEE Trans. Indust. Inf.
Collaborative filtering in a non-uniform world: learning with the weighted trace norm
Proceedings of the Twenty-fourth Annual Conference on Neural Information Processing Systems
Collaborative Gaussian processes for preference learning
Proceedings of the Twenty-sixth Annual Conference on Neural Information Processing Systems
A nonnegative latent factor model for large-scale sparse matrices in recommender systems via alternating direction method
IEEE Trans. Neural Netw. Learn. Syst.
Efficient extraction of non-negative latent factors from high-dimensional and sparse matrices in industrial applications
Proceedings of Sixteenth IEEE International Conference on Data Mining
A novel approach to extracting non-negative latent factors from non-negative big sparse matrices
IEEE Access
An incremental-and-static-combined scheme for matrix-factorization-based collaborative filtering
IEEE Trans. Autom. Sci. Eng.
An efficient non-negative matrix-factorization-based approach to collaborative filtering for recommender systems
IEEE Trans. Indust. Inf.
Predicting quality of service for selection by neighborhood-based collaborative filtering
IEEE Trans. Syst. Man Cybern. Syst.
Collaborative web service QOS prediction via neighborhood integrated matrix factorization
IEEE Trans. Serv. Comput.
Inverse-free extreme learning machine with optimal information updating
IEEE Trans. Cybern.
A novel switching delayed PSO algorithm for estimating unknown parameters of lateral flow immunoassay
Cogn. Comput.
Deep belief networks for quantitative analysis of a gold immunochromatographic strip
Cogn. Comput.
A hybrid EKF and switching PSO algorithm for joint state and parameter estimation of lateral flow immunoassay models
IEEE/ACM Trans. Comput. Biol. Bioinf.
Inferring nonlinear lateral flow immunoassay state-space models via an unscented Kalman filter
Sci. China Inf. Sci.
Collaborative video reindexing via matrix factorization
ACM Trans. Multimedia Comput. Commun. Appl.
Tracking mobile users in wireless networks via semi-supervised colocalization
IEEE Trans. Pattern Anal. Mach. Intel.
Addressing the cold-start problem in location recommendation using geo-social correlations
Data Mining Knowl. Disc.
Location-based and preference-aware recommendation using sparse geo-social networking data
Proceedings of the Twentieth ACM International Conference on Advances in Geographic Information Systems
Geo topic model: joint modeling of user’s activity area and interests for location recommendation
Proceedings of the Sixth ACM International Conference on Web Search & Data Mining
Learning geographical preferences for point-of-interest recommendation
Proceedings of the Nineteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Exploiting geographical influence for collaborative point-of-interest recommendation
Proceedings of the Thirty-fourth ACM SIGIR Conference on Research and Development in Information Retrieval
Fused matrix factorization with geographical and social influence in location-based social networks
Proceedings of the Twenty-sixth AAAI Conference on Artificial Intelligence
gscorr: modeling geo-social correlations for new check-ins on location-based social networks
Proceedings of the Twenty-first ACM International Conference on Information and Knowledge Management
Location recommendation in location-based social networks using user check-in data
Proceedings of the Twenty-first ACM international Conference on Advances in Geographic Information Systems
Location recommendation for out-of-town users in location-based social networks
Proceedings of the Twenty-second ACM international conference on Information & Knowledge Management
IGSLR: personalized geo-social location recommendation: a kernel density estimation approach
Proceedings of the Twenty-first ACM International Conference on Advances in Geographic Information Systems
Cited by (67)
NRDL: Decentralized user preference learning for privacy-preserving next POI recommendation
2024, Expert Systems with ApplicationsModified node2vec and attention based fusion framework for next POI recommendation
2024, Information FusionKDRank: Knowledge-driven user-aware POI recommendation
2023, Knowledge-Based SystemsIncorporating textual reviews in the learning of latent factors for recommender systems
2022, Electronic Commerce Research and ApplicationsCitation Excerpt :It is difficult for them to find suitable ones among a huge number of items that they have access to on applications. Recommender systems are on a mission to address this challenge (Tamhane et al., 2017; Pichl et al., 2017; Gao et al., 2018; Liu et al., 2021). Their task is to discover hidden patterns in item preferences collected from users, thereby recommending the items best suited to the users (Mashal et al., 2016; Chambua & Niu, 2021; Chehal et al., 2021).
Leveraging social influence based on users activity centers for point-of-interest recommendation
2022, Information Processing and ManagementA survey on deep learning based Point-of-Interest (POI) recommendations
2022, NeurocomputingCitation Excerpt :To achieve better performance than vanilla MF methods, Bayesian Personalized Ranking (BPR [21]) methods have been employed [22–28,8]. Other traditional approaches like Support Vector Machine (SVM) [29], Collaborative Filtering [30–35], Gaussian Modeling [36], Transitive Dissimilarity [37] have also been exploited in different works for personalized POI recommendation. One major shortcoming of all these approaches lies in feature engineering, and explicit feature engineering requires sufficient domain expertise.
Rong Gao received the M.S. degree in Computer Science in 2007 from Hubei University, Wuhan, China. He is currently pursuing the Ph.D. degree for Computer Science in Computer School, Wuhan University, China. His research interests include data mining and intelligent recommendation.
Jing Li received the Ph.D. degree from Wuhan University, Wuhan, China, in 2006. He is currently a Professor in Computer School of Wuhan University, Wuhan, China. His research interests include data mining and multimedia technology.
Xuefei Li received the Ph.D. degree from Wuhan University in 2007, Wuhan, China. He is currently an Associate Professor in Computer School of Wuhan University, Wuhan, China. His current research interest include data mining and Multimedia technology.
Chenfang Song received the Ph.D. degree from Zhejiang University in 2007, Hangzhou, China. He is currently an Assistant Professor in Computer School of Wuhan University, Wuhan, China. His current research interests include visualization analysis and location service.
Yifei Zhou received the M.S degree in Software Engineering from Wuhan University in 2013, Wuhan, China. She is currently working for the Ph.D. degree also at Wuhan University .Her main research interest include data mining and pattern recognition.