Exploring temporal effects for location recommendation on location-based social networks
Published 12 October 2013
Huiji Gao, Jiliang Tang, Xia Hu, Huan Liu
Citations513
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A novel location recommendation framework is introduced, based on the temporal properties of user movement observed from a real-world LBSN dataset, which exhibits the significance of temporal patterns in explaining user behavior, and demonstrates their power to improve location recommendation performance.
Abstract
Location-based social networks (LBSNs) have attracted an inordinate number of users and greatly enriched the urban experience in recent years. The availability of spatial, temporal and social information in online LBSNs offers an unprecedented opportunity to study various aspects of human behavior, and enable a variety of location-based services such as location recommendation. Previous work studied spatial and social influences on location recommendation in LBSNs. Due to the strong correlations between a user's check-in time and the corresponding check-in location, recommender systems designed for location recommendation inevitably need to consider temporal effects. In this paper, we introduce a novel location recommendation framework, based on the temporal properties of user movement observed from a real-world LBSN dataset. The experimental results exhibit the significance of temporal patterns in explaining user behavior, and demonstrate their power to improve location recommendation performance.
Keywords
Social SciencesComputer Science
NatureLearning the parts of objects by non-negative matrix factorization
14,055 Citations1999Daniel D. Lee, H. Sebastian Seung
An algorithm for non-negative matrix factorization is demonstrated that is able to learn parts of faces and semantic features of text and is in contrast to other methods that learn holistic, not parts-based, representations.
ComputerMatrix Factorization Techniques for Recommender Systems
11,675 Citations2009Yehuda Koren, Robert Bell +1 more
As the Netflix Prize competition has demonstrated, matrix factorization models are superior to classic nearest neighbor techniques for producing product recommendations, allowing the incorporation of additional information such as implicit feedback, temporal effects, and confidence levels.
Factorization meets the neighborhood
3,876 Citations2008Yehuda Koren
The factor and neighborhood models can now be smoothly merged, thereby building a more accurate combined model and a new evaluation metric is suggested, which highlights the differences among methods, based on their performance at a top-K recommendation task.
Friendship and mobility
2,910 Citations2011Eunjoon Cho, Seth A. Myers +1 more
A model of human mobility that combines periodic short range movements with travel due to the social network structure is developed and it is shown that this model reliably predicts the locations and dynamics of future human movement and gives an order of magnitude better performance.
SoRec
1,427 Citations2008Hao Ma, Haixuan Yang +2 more
A factor analysis approach based on probabilistic matrix factorization to solve the data sparsity and poor prediction accuracy problems by employing both users' social network information and rating records is proposed.
Exploiting geographical influence for collaborative point-of-interest recommendation
1,097 Citations2011Mao Ye, Peifeng Yin +2 more
This paper argues that the geographical influence among POIs plays an important role in user check-in behaviors and model it by power law distribution, and develops a collaborative recommendation algorithm based on geographical influence based on naive Bayesian.
Proceedings of the International AAAI Conference on Web and Social MediaExploring Millions of Footprints in Location Sharing Services
696 Citations2021Zhiyuan Cheng, James Caverlee +2 more
It is found that LSS users follow the “Levy Flight” mobility pattern and adopt periodic behaviors; while geographic and economic constraints affect mobility patterns, so does individual social status; and Content and sentiment-based analysis of posts associated with checkins can provide a rich source of context for better understanding how users engage with these services.
Proceedings of the AAAI Conference on Artificial IntelligenceFused Matrix Factorization with Geographical and Social Influence in Location-Based Social Networks
574 Citations2021Cheng Chen, Haiqin Yang +2 more
This paper is the first to fuse MF with geographical and social influence for POI recommendation in LBSNs by capturing the geographical influence via modeling the probability of a user’s check-in on a location as a Multi-center Gaussian Model (MGM).
Location recommendation for location-based social networks
508 Citations2010Mao Ye, Peifeng Yin +1 more
A friend-based collaborative filtering approach for location recommendation based on collaborative ratings of places made by social friends is developed, and a variant of FCF technique, namely Geo-Measured FCF (GM-FCF), based on heuristics derived from observed geospatial characteristics in the Foursquare dataset is proposed.
Proceedings of the International AAAI Conference on Web and Social MediaAn Empirical Study of Geographic User Activity Patterns in Foursquare
496 Citations2021Anastasios Noulas, Salvatore Scellato +2 more
How scientific researchers could utilise data generated in Location-based Social Networks to attain a deeper understanding of human mobility and how developers may take advantage of such systems to enhance applications such as recommender systems is informed.
ACM Transactions on the WebRecommending friends and locations based on individual location history
480 Citations2011Yu Zheng, Lizhu Zhang +3 more
A framework, referred to as a hierarchical-graph-based similarity measurement (HGSM), is proposed to uniformly model each individual's location history, and effectively measure the similarity among users, which outperforms related similarity measures, namely similarity-by-count, cosine similarity, and Pearson similarity measures.
Proceedings of the International AAAI Conference on Web and Social MediaSocio-Spatial Properties of Online Location-Based Social Networks
434 Citations2021Salvatore Scellato, Anastasios Noulas +2 more
This work presents a comprehensive study of the spatial properties of the social networks arising among users of three main popular online location-based services, and provides evidence that mechanisms akin to gravity models may influence how these social connections are created over space.
mTrust
350 Citations2012Jiliang Tang, Huiji Gao +1 more
Experimental results on real-world data from Epinions and Ciao show that the work of discerning multi-faceted trust can be applied to improve the performance of tasks such as rating prediction, facet-sensitive ranking, and status theory.
Proceedings of the International AAAI Conference on Web and Social MediaExploring Social-Historical Ties on Location-Based Social Networks
248 Citations2021Huiji Gao, Jiliang Tang +1 more
This paper proposes a social-historical model that integrates the social and historical effects and assesses the role of social correlation in user's check-in behavior on LBSNs, and captures the property of user's checking-in history in forms of power-law distribution and short-term effect.
A sentiment-enhanced personalized location recommendation system
229 Citations2013Dingqi Yang, Daqing Zhang +2 more
This research proposes a hybrid user location preference model by combining the preference extracted from check-ins and text-based tips which is processed using sentiment analysis techniques and develops a location based social matrix factorization algorithm that takes both user social influence and venue similarity influence into account in location recommendation.
eTrust
215 Citations2012Jiliang Tang, Huiji Gao +2 more
This paper proposes a framework of evolution trust, eTrust, which exploits the dynamics of user preferences in the context of online product review and performs experiments to show how the exploitation of trust evolution can help improve the performance of online applications such as rating and trust prediction.
Workshop on Online Social NetworksDistance matters: geo-social metrics for online social networks
209 Citations2010Salvatore Scellato, Cecilia Mascolo +2 more
This paper presents a graph analysis based approach to study social networks with geographic information and new metrics to characterize how geographic distance affects social structure, and demonstrates that different social networking services exhibit different geo-social properties.
gSCorr
201 Citations2012Huiji Gao, Jiliang Tang +1 more
This paper proposes a geo-social correlation model to capture social correlations on LBSNs considering social networks and geographical distance, and demonstrates that this approach properly models the social correlations of a user's new check-ins by considering various correlation strengths and correlation measures.
A recommendation system for spots in location-based online social networks
149 Citations2011Betim Berjani, Thorsten Strufe
A personalized recommender for places in location-based OSNs, based on the check-ins of the entire user base is proposed, and the feasability of using Collaborative Filtering techniques to make personalized recommendation of potentially interesting spots is confirmed.
Nonnegative Matrix Factorization for Combinatorial Optimization: Spectral Clustering, Graph Matching, and Clique Finding
133 Citations2008Chris Ding, Tao Li +1 more
This paper proposes several NMF inspired algorithms to solve different data mining problems, including multi-way normalized cut spectral clustering, graph matching of both undirected and directed graphs, and maximal clique finding on both graphs and bipartite graphs.
What you are is when you are
110 Citations2011Mao Ye, Krzysztof Janowicz +2 more
This work extracts user check-ins from massive real-world data crawled from Location-based Social Networks to understand the temporal dimension of Points Of Interest.
Urban point-of-interest recommendation by mining user check-in behaviors
103 Citations2012Josh Jia-Ching Ying, Eric Hsueh-Chan Lu +2 more
The core idea of UPOI-Mine is to build a regression-tree-based predictor in the normalized check-in space so as to support the prediction of interestingness of POI related to each user's preference.
Mobile Location Prediction in Spatio-Temporal Context
94 Citations2012Huiji Gao, Jiliang Tang +1 more
A novel location prediction model is proposed that considers not only the spatial historical trajectories, but also the temporal periodic patterns, and obtains significant improvement compared to the state-of-the-art approaches.
Evaluating geo-social influence in location-based social networks
92 Citations2012Chao Zhang, Lidan Shou +3 more
This paper performs an in-depth analysis of the geo-social correlations among LBSN users at event level, and proposes a unified influence metric that combines a novel social proximity measure named penalized hitting time, with a geographical weight function modeled by power law distribution.
Proceedings of the International AAAI Conference on Web and Social MediaLocation3: How Users Share and Respond to Location-Based Data on Social
69 Citations2021Jonathan Chang, Eric Sun
A model to predict friendship based on check-in count is constructed and it is shown that cocheck-ins has a statistically significant effect on friendship.
Lecture notes in computer scienceA Study of Recommending Locations on Location-Based Social Network by Collaborative Filtering
57 Citations2012Dequan Zhou, Bin Wang +2 more
The experimental results show that PLSA recommender with the probability utilization outperforms other combinations of recommenders and utilizations for recommending locations to users on LBSN.
Checking in or checked in
23 Citations2012Eric Malmi, Trinh Minh Tri +1 more
This paper analyzes the differences and similarities of manual check-ins from Foursquare and automatic check-in data from Nokia's Mobile Data Challenge to address the question of whether it is possible to find matching places across the two check- in systems.
Location Type Classification Using Tweet Content
18 Citations2012Haibin Liu, Bo Luo +1 more
Probabilistic text classification models are extended to incorporate temporal features and user history information in terms of probabilistic priors and Experimental results show that the extensions can boost classification accuracy effectively.