Users In Location-based Social Networks Research Articles

Conditional heavy hitter monitoring and application of heterogeneous graph streams based on sketches

Graph streams offer valuable insights into real network evolution in the era of big data. Heavy hitters and conditional heavy hitters focus on identifying entities with significant network traffic, revealing network data characteristics. In this paper, we present two methods, BLSketch and MHLSketch, for identifying heavy hitters and conditional heavy hitters in heterogeneous graph streams. BLSketch uses the bidirectional mapper, Bimap, for efficient query response times while retaining candidate information. MHLSketch uses min heap to preserve a minimal set of candidates to minimize storage space, excelling in space efficiency. The two methods can be incorporated with any sketch based graph summarization method, showing excellent adaptability. Experimental results on four real-world heterogeneous datasets of varying scales with the largest dataset containing millions of edges demonstrate our methods significantly improve the quality of query answering, outperforming state-of-the-art methods, with precision close to 1 and average relative error close to 0. We further combine our methods with density clustering to introduce the SDC model, which efficiently identifies hot regions and key users in Location-Based Social Networks (LBSN). In experiments, SDC outperforms traditional clustering by reducing up to 93.1% of cold Points of Interest (POIs) and shows strong potential for practical applications.

Meta Path-Aware Recommendation Method Based on Non-Negative Matrix Factorization in LBSN

Location-based social networks (LBSN) is a new type of heterogeneous information network (HIN). The check-in data usually has the characteristics of a large amount of data and high sparsity. It is a problem worth studying how to effectively discover its complex community structure and accurately recommend it to users. Most HIN-based recommendation methods rely on path-based similarity, which cannot fully mine latent structure features of LBSN users and items. This paper proposes a meta-path-aware common clustering recommendation method MPNMF (meta-path-aware non-negative matrix factorization), based on non-negative matrix tri-factorization. By establishing the objective function based on non-negative matrix tri-factorization and second-order meta-path method, LBSN users and points of interest are integrated with their multi-dimensional heterogeneous relationships. The interrelated user clusters and interest point clusters can be obtained, effectively alleviating the influence of data sparsity. To solve the initial value problem of the model, this method uses the spectral cluster method, which provides a good initial value for the construction of the prediction model. It improves the operational efficiency of the model and the precision of model recommendations. Experiments on the real LBSN datasets show that the proposed method has a high recommendation precision and recall.

Trust-aware location recommendation in location-based social networks: A graph-based approach

With the increase in the use of mobile devices having location-related capabilities, the use of Location-Based Social Networks (LBSN) has also increased, allowing users to share location-embedded information with other users in the social network. By leveraging check-in activities provided by LBSNs, personalized recommendations can be provided. Trust is an important concept in social networks to improve recommendation quality. In this work, we develop a method for predicting the trust scores of LBSN users and propose a trust-aware recommendation technique, TLoRW, to recommend locations to users based on their previous check-ins, the social network, and predicted trust scores of users. In the proposed model, global trust score of user is generated on the basis of check-in history. In addition to trust, spatial context is anther important aspect of TLoRW to generate location recommendations based on the current location of a user. The proposed algorithm runs on a contextual subgraph rather full graph, relaxing the computing resource requirement. We represent a given LBSN with a undirected graph model. Recommendation scores of the locations are generated as the result of the random walk performed on the trust augmented LBSN subgraph. A comprehensive evaluation of TLoRW is conducted by comparing its recommendation performance against baseline techniques, as well as state-of-the-art trust-aware recommendation approaches in the literature, based on benchmark datasets. The experiments reveal that the trust information incorporated into random-walk-based approach improves the accuracy of the recommended locations @5 by minimum 5%.

Trust-aware location recommendation for user groups

Recommender systems have become indispensable part of online environments. Product recommendations in ecommerce applications, location recommendations in location related applications, and user and post recommendations in online social networks are just a few examples in the world of online recommendations. The recommendations generated in such environments are mostly for individuals. However, increasing use of social networks and online communities lead to need for generating recommendations for a group of users for joint activities, such as eating out as a group or seeing a movie with friends. In the literature, there are studies proposing recommendation solutions for groups, but the number of such studies is very limited. In this work, we address the problem of location recommendation to a group of users, and the proposed solutions are based on Random Walk with Restart (RWR) algorithm on the social network graph. Another novel aspect of the proposed work is the use of trust factor of users in location-based social networks (LBSNs). In generating group recommendations, we follow two alternative paths. The first one aggregates the location recommendations that are generated with the Random Walk algorithm for each member in the group, taking the preferences and objectivity scores of the individuals into account. The second one is based on creating a group profile by blending preferences and venue category types, and using this group profile to run the Random Walk algorithm once. In both approaches trust factor of users is incorporated into the solutions within the social network graph. The experiments conducted on the data collected from the location based social network platform Foursquare have shown that the trust factor of users improves the performance of group recommendation system and the proposed algorithm provides recommendations to groups with high accuracy compared to the baselines.

Location-Visiting Characteristics Based Privacy Protection of Sensitive Relationships

In the era of Internet of Things (IoT), the problem of the privacy leakage of sensitive relationships is critical. This problem is caused by the spatial–temporal correlation between users in location-based social networks (LBSNs). To solve this problem, a sensitive relationship-protection algorithm based on location-visiting characteristics is proposed in this paper. Firstly, a new model based on location-visiting characteristics is proposed for calculating the similarity between users, which evaluates check-in features of users and locations. In order to avoid an adversary inferring sensitive relationship privacy and to ensure the utility of data, our proposed algorithm adopts a heuristic rule to evaluate the impact of deduction contributions and information loss caused by data modifications. In addition, location-search technology is proposed to improve the algorithm’s execution efficiency. The experimental results show that our proposed algorithm can effectively protect the privacy of sensitive data.

PredicTour: Predicting Mobility Patterns of Tourists Based on Social Media User’s Profiles

This paper proposes PredicTour, an approach to process check-ins made by users of location-based social networks (LBSNs), and predict mobility patterns of tourists visiting new countries with or without previous visiting records. PredicTour is composed of three key parts: mobility modeling, profile extraction, and tourist mobility prediction. In the first part, sequences of check-ins within a time interval are associated with other user information to produce a new structure called “mobility descriptor”. In the profile extraction, self-organizing maps and fuzzy C-means work jointly to group users according to their mobility descriptors. PredicTour then identifies tourist profiles and estimates mobility patterns of tourists visiting new countries. When comparing the performance of PredicTour with three well-known machine learning-based models, the results indicate that PredicTour outperforms the baseline approaches. Therefore, it is a good alternative for predicting and understanding international tourists’ mobility, which has an economic impact on the tourism industry when services and logistics across international borders should be provided. The proposed approach can be used in different applications, such as in recommender systems for tourists or in decision-making support for urban planners interested in improving tourists’ experiences and attractiveness of venues through personalized services.

Sparse User Check-in Venue Prediction By Exploring Latent Decision Contexts From Location-Based Social Networks

The proliferation of online Location-Based Social Networks (LBSN) has offered unprecedented opportunities for understanding fine-grained spatio-temporal behaviors of users and developing new location-aware applications. In this article, we focus on the problem of “Sparse User Check-in Venue Prediction,” where the goal is to predict the next venue LBSN users will visit by exploiting their sparse online check-in traces and the latent decision contexts. While efforts have been made to predict users’ check-in traces on a LBSN, several important challenges still exist. First, check-in traces contributed by LBSN users are often too sparse to provide sufficient evidence for a reliable prediction, especially when the prediction space is huge (e.g., hundreds of thousands of venues in large cities). Second, the user's decision context on which venue to visit next is often latent and has not been incorporated by current venue prediction models. Third, the dynamic and non-deterministic dependency between check-ins is either ignored or replaced by a simplified “consecutiveness” assumption in existing solutions, leading to sub-optimal prediction results. In this article, we develop a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Context-aware Sparse Check-in Venue Prediction (CSCVP)</i> scheme inspired by natural language processing techniques to address the above challenges. In particular, CSCVP predicts the venue category information and explores the similarity between users to address data sparsity challenge by significantly reducing the prediction space. It also leverages the Probabilistic Latent Semantic Analysis (PLSA) model to incorporate the user decision context into the prediction model. Finally, we develop a novel Temporal Adaptive Ngram (TA-Ngram) model in CSCVP to capture the dynamic and non-deterministic dependency between check-ins. We evaluate CSCVP using three real-world LBSN datasets. The results show that our scheme significantly improves accuracy (30.9 percent improvement) of the state-of-the-art user check-in venue prediction solutions.

Locating Identities in Time: An Examination of the Formation and Impact of Temporality on Presentations of the Self through Location-Based Social Networks

Studies of identity and location-based social networks (LBSN) have tended to focus on the performative aspects associated with marking one's location. Yet these studies often present this practice as being an a priori aspect of locative media. What is missing from this research is a more granular understanding of how this process develops over time. Accordingly, we focus on the first 6 weeks of 42 users beginning to use an LBSN we designed and named GeoMoments . Through our analysis of our users' activities, we contribute to understanding identity and LBSN in two distinct ways. First, we show how LBSN users develop and perform self-identity over time. Second, we highlight the extent these temporal processes reshape the behaviors of users. Overall, our results illustrate that although a performative use of GeoMoments does evolve, this development does not occur in a vacuum. Rather, it occurs within the dynamic context of everyday life, which is prompted, conditioned, and mediated by the way the affordances of GeoMoments digitally organize and archive past locational traces.

Exploiting Semantic Annotations for Clustering Geographic Areas and Users in Location-based Social Networks

Location-Based Social Networks (LBSN) present so far the most vivid realization of the convergence of the physical and virtual social planes. In this work we propose a novel approach on modeling human activity and geographical areas by means of place categories. We apply a spectral clustering algorithm on areas and users of two metropolitan cities on a dataset sourced from the most vibrant LBSN, Foursquare. Our methodology allows the identification of user communities that visit similar categories of places and the comparison of urban neighborhoods within and across cities. We demonstrate how semantic information attached to places could be plausibly used as a modeling interface for applications such as recommender systems and digital tourist guides.

Privacy and the City: User Identification and Location Semantics in Location-Based Social Networks

With the advent of GPS enabled smartphones, an increasing number of users is actively sharing their location through a variety of applications and services. Along with the continuing growth of Location-Based Social Networks (LBSNs), security experts have increasingly warned the public of the dangers of exposing sensitive information such as personal location data. Most importantly, in addition to the geographical coordinates of the user's location, LBSNs allow easy access to an additional set of characteristics of that location, such as the venue type or popularity. In this paper, we investigate the role of location semantics in the identification of LBSN users. We simulate a scenario in which the attacker's goal is to reveal the identity of a set of LBSN users by observing their check-in activity. We then propose to answer the following question: what are the types of venues that a malicious user has to monitor to maximize the probability of success? Conversely, when should a user decide whether to make his/her check-in to a location public or not? We perform our study on more than 1 million check-ins distributed over 17 urban regions of the United States. Our analysis shows that different types of venues display different discriminative power in terms of user identity, with most of the venues in the "Residence" category providing the highest re-identification success across the urban regions. Interestingly, we also find that users with a high entropy of their check-ins distribution are not necessarily the hardest to identify, suggesting that it is the collective behaviour of the users' population that determines the complexity of the identification task, rather than the individual behaviour.

Joint obfuscation of location and its semantic information for privacy protection

Location-based social networks (LBSNs) such as Foursquare and Facebook enable users to share with each other, their (geographical) locations together with the semantic information associated with their locations. The semantic information captures the type of a location and is usually represented by a semantic tag like “restaurant”, “museum”, “school”, etc. Semantic tag sharing increases the threat to users’ location privacy (which is already at risk because of location sharing) and it also puts users’ semantic location privacy at risk. The existing solution to protect the location privacy and the semantic location privacy of users in such LBSNs is to obfuscate the location and the semantic tag independently of each other in a so called disjoint obfuscation approach. Thus, in this approach, the semantic tag is obfuscated i.e., replaced by a more general tag. Also, the location is obfuscated i.e., replaced by a generalized area (called the cloaking area) made of the actual location and some of its nearby locations. However, since in this approach the location obfuscation is performed in a semantic-oblivious manner, an adversary can still increase his chance to infer the actual location and the actual semantic tag by filtering out the locations in the cloaking area that are not semantically compatible with the obfuscated semantic tag. In this work, we address this issue by proposing a joint obfuscation approach in which the location obfuscation is performed based on the result of the semantic tag obfuscation. We also provide a formal framework for evaluation and comparison of our joint approach with the disjoint approach. By running an experimental evaluation on a dataset of real-world user traces collected from six different cities, we show that in almost all cases (i.e., in different cities and with different obfuscation parameters), the joint approach outperforms the disjoint approach in terms of location privacy protection and the semantic location privacy protection. Based on the evaluation results, we also discuss how different obfuscation parameters and the choice of the city can affect the performance of the obfuscation approaches. In particular, we show how changing these parameters can improve the performance of the joint approach.

FACF: fuzzy areas-based collaborative filtering for point-of-interest recommendation

Several online social networks collect information from their users' interactions (co-tagging of photos, co-rating of products, etc.) producing a large amount of activity-based data. As a consequence, this kind of information is used by these social networks to provide their users with recommendations about new products or friends. Moreover, recommendation systems (RS) become capable to predict a person's activity with no special infrastructure or hardware, such as RFID tags, or by using video and audio. In that sense, we propose a technique to provide personalised points-of-interest (POIs) recommendations for users of location-based social networks (LBSNs). Our technique assumes users' preferences can be characterised by their visited locations, which is shared by them on LBSN, collaboratively exposing important features as, for instance, areas-of-interest (AOIs) and POIs popularity. Therefore, our technique, named fuzzy areas-based collaborative filtering, uses users' activities to model their preferences and recommend the next visits to them. We have performed experiments over two real LBSN datasets and the obtained results have shown our technique outperforms location collaborative filtering at almost all of the experimental evaluation. Therefore, by fuzzy clustering of AOIs, FACF is suitable to check the popularity of POIs to improve POIs recommendation.

FACF: fuzzy areas-based collaborative filtering for point-of-interest recommendation

Several online social networks collect information from their users' interactions (co-tagging of photos, co-rating of products, etc.) producing a large amount of activity-based data. As a consequence, this kind of information is used by these social networks to provide their users with recommendations about new products or friends. Moreover, recommendation systems (RS) become capable to predict a person's activity with no special infrastructure or hardware, such as RFID tags, or by using video and audio. In that sense, we propose a technique to provide personalised points-of-interest (POIs) recommendations for users of location-based social networks (LBSNs). Our technique assumes users' preferences can be characterised by their visited locations, which is shared by them on LBSN, collaboratively exposing important features as, for instance, areas-of-interest (AOIs) and POIs popularity. Therefore, our technique, named fuzzy areas-based collaborative filtering, uses users' activities to model their preferences and recommend the next visits to them. We have performed experiments over two real LBSN datasets and the obtained results have shown our technique outperforms location collaborative filtering at almost all of the experimental evaluation. Therefore, by fuzzy clustering of AOIs, FACF is suitable to check the popularity of POIs to improve POIs recommendation.

Knowledge Graph-Based Spatial-Aware User Community Preference Query Algorithm for LBSNs

Abstract User community preference in Location-Based Social Networks (LBSNs) can meet the diversified location demands of group LBSN users. Although individual's location-based service recommendation or personal spatial preference query problem has been well addressed by many studies, user group or user community preference query is still under way and most only consider the spatial distance factor, which causes accuracy cannot satisfy user demands. To solve the user community spatial preference problem and improve its performance, a knowledge graph-based spatial-aware user community preference query algorithm, Type R-tree (tR-tree) Query Algorithm (TRQA) is proposed to effectively discover user's community preference from LBSNs considering both location semantic information and preference weight of users' Points of Interest (POIs). To achieve this goal, this paper first leverages the tR-tree spatial index to improve query efficiency. Then a community satisfaction degree model based on knowledge graphs is introduced to comprehensively evaluate whether the POI can best meet the preference requirements of a user community. The experimental results show that TRQA has outperformed Perceptual Quality Adaptation Algorithm (PQA) in terms of pruning efficiency and query time. The query time of our proposed algorithm is 80% shorter than PQA as the number of users in the user community changes.

Effective neural architectures for context-aware venue recommendation

Users in Location-Based Social Networks (LBSNs), such as Yelp and Foursquare, can search for interesting venues such as restaurants and museums to visit, or share their location with their friends by making an implicit feedback (e.g. checking in at venues they have visited). The users can also leave explicit feedback on the venues they have visited by providing ratings and/or comments. Such explicit and implicit feedback by the users provide rich information about both users and venues, and thus can be leveraged to study the users' movement in urban cities, as well as enhance the quality of personalised venue recommendations. Unlike traditional recommendation systems (e.g. book and movie recommendation systems), making effective venue recommendations is more challenging because we need to take into account the users' current context (e.g. time of the day, user's current location as well as his recently visited venues). In this thesis, based upon Matrix Factorisation (MF) and Bayesian Personalised Ranking (BPR) models, we aim to generate effective context-aware venue recommendation that a user may wish to visit based on the user's historical explicit and implicit feedbacks, the user's contextual information (e.g. the user's current location and time of the day) and additional information (e.g. the geographical location of venues and users' social relationships). To achieve this goal, we need to address the following challenges: namely (C1) modelling the users' preferences and the characteristic of venues, (C2) capturing the complex structure of user-venue interactions in a Collaborative Filtering manner, (C3) modelling the users' short-term ( dynamic ) preferences from the sequential order of user's observed feedback as well as the contextual information associated with the successive feedback, (C4) generating accurate top-K venue recommendations based on the users' preferences using a pairwise ranking-based model and (C5) appropriately sampling potential negative instances to train a ranking-based model. First, to address challenge C1 , we leverage the users' explicit feedback (e.g. their ratings and the textual content of the comments) and additional information (e.g. users' social relationships) to effectively model the users' preferences and the characteristics of venues. In particular, we propose a novel regularisation technique [1] and a factorisation-based model [2] that leverages the users' explicit feedback and the additional information to improve the rating prediction accuracy of the traditional MF model. Experiments conducted on a large scale rating dataset on LBSN demonstrate that the textual content of comments plays an important role in enhancing the accuracy of rating prediction. Second, we investigate how to leverage the users' implicit feedback and additional information such as the users' social relationship and the geographical location of venues to improve the quality of top-K venue recommendations. In particular, to address challenges C4 and C5 , we propose a novel pairwise ranking-based framework for top-K venue recommendations [3] that can incorporate multiple sources of additional information (e.g. the users' social relationship and the geographical location of venues) to effectively sample the potential negative instances. Experimental results on three large scale checkin and rating datasets from LBSNs demonstrate that the social correlations and the geographical influences play an important role to the quality of sampled negative instances and hence can improve the quality of top-K venue recommendations. Finally, to address challenges C2 and C3 , we propose a framework for sequential-based venue recommendations [4] that exploits Deep Neural Network (DNN) models to effectively capture the complex structure of user-venue interactions and the users' long-term ( dynamic ) preferences from their sequential order of checkins. Moreover, we propose a novel Recurrent Neural Network (RNN) architecture [5] that can effectively incorporate the contextual information associated with the successive implicit feedback (e.g. the time interval and the geographical distance between two successive checkins) to generate high quality context-aware venue recommendations. Experimental results on three large scale checkin and rating datasets from LBSNs demonstrate the effectiveness and robustness of our proposed framework and architecture for context-aware venue recommendations. Supervisors Dr. Craig Macdonald (University of Glasgow), Prof. Iadh Ounis (University of Glasgow) Available from : http://theses.gla.ac.uk/76735/

On A Novel Adaptive UAV-Mounted Cloudlet-Aided Recommendation System for LBSNs

Location Based Social Networks (LBSNs) have recently emerged as a hot research area. However, the high mobility of LBSN users and the need to quickly provide access points in their interest zones present a unique research challenge. In order to address this challenge, in this paper, we consider the Unmanned Aerial Vehicles (UAVs) to be a viable candidate to promptly form a wireless, meshed offloading backbone to support the LBSN data sensing and relevant data computations in the LBSN cloud. In the considered network, UAV-mounted cloudlets are assumed to carry out adaptive recommendation in a distributed manner so as to reduce computing and traffic load. Furthermore, the computational complexity and communication overhead of our proposed adaptive recommendation are analyzed. The effectiveness of the proposed recommendation system in the considered LBSN is evaluated through computer-based simulations. Simulation results demonstrate that our proposal achieves much improved performance compared to conventional methods in terms of accuracy, throughput, and delay.

Context-aware user preferences prediction on location-based social networks

Recently, the increasing number of mobile users in location-based social networks (LBSNs) has generated large amounts of data, which provides unprecedented opportunities to study mobile user preferences for location recommendation. However, the huge amount of LBSNs data and sparsity problem limited improvements of efficiency and accuracy on mobile user preferences for location recommendation. This paper proposes a context-aware user preferences prediction algorithm for location recommendation on LBSNs. It introduces cloud model and category information into estimating the similarity of users and locations. Furthermore, it predicts user preferences of new locations according to the categories of new locations and user visited. In particular, the algorithm is parallelized with MapReduce framework for significant improvement in efficiency. Experimental results on Foursquare dataset demonstrate the performance gains of the algorithm.

Location perspective-based neighborhood-aware POI recommendation in location-based social networks

As an effective way to help users find attractive locations and meet their individual needs, point-of-interest (POI) recommendation has become an important application in location-based social networks (LBSNs). Although the geographical influence has been reported as an effective factor for improving POI recommendation accuracy, previous work mainly models it from the user perspective instead of location perspective. Intuitively, neighboring POIs tend to be visited by similar users, which implies that modeling geographical relationships from a location perspective can simulate users’ behavior more reasonably. Moreover, different from traditional recommendation problems, users in LBSNs often express their interests only by checking in different POIs, which is a kind of implicit feedback. In other words, we can easily get the POIs that the users have visited, but it is hard to get the ones that the users do not like. We cannot use a common approach to distinguish these negative values directly. Based on the above observations, this work concentrates on exploiting the geographical relationships among POIs from a location perspective for implicit problem, where a location neighborhood-aware weighted probabilistic matrix factorization is proposed (L-WMF). To be specific, the weighted probabilistic matrix factorization (WMF) that can deal with implicit feedback is first introduced as our basic POI recommendation method. Then, we incorporate the geographical relationships among POIs into the WMF as the regularization terms to exploit the geographical characteristics from a location perspective. Finally, we conduct several experiments to evaluate our L-WMF method on two real-world datasets, and the experimental results indicate that the L-WMF is more effective and can reach better performance than other related methods.

Multi-Context Integrated Deep Neural Network Model for Next Location Prediction

The prediction of next location for users in location-based social networks has become an increasing significant requirement since it can benefit both users and business. However, existing methods lack an integrated analysis of sequence context, input contexts, and user preferences in a unified way, and result in an unsatisfactory prediction. Moreover, the interaction between different kinds of input contexts has not been investigated. In this paper, we propose a multi-context integrated deep neural network model (MCI-DNN) to improve the accuracy of the next location prediction. In this model, we integrate sequence context, input contexts, and user preferences into a cohesive framework. First, we model sequence context and interaction of different kinds of input contexts jointly by extending the recurrent neural network to capture the semantic pattern of user behaviors from check-in records. After that, we design a feedforward neural network to capture high-level user preferences from check-in data and incorporate that into MCI-DNN. To deal with different kinds of input contexts in the form of multi-field categorical, we adopt embedding representation technology to automatically learn dense feature representations of input contexts. Experimental results on two typical real-world data sets show that the proposed model outperforms the current state-of-the-art approaches by about 57.12% for Foursquare and 76.4% for Gowalla on average regarding F1-score@5.

Hidden community identification in location-based social network via probabilistic venue sequences

Location-based Social Networks (LBSN) such as Foursquare have become ubiquitous due to the vast spread of smart mobile devices. The users of LBSN can check in at any locations, write tips, share comments, etc. LBSN has attracted much research attention due to the fact that the large volume of check-ins provides an unprecedented channel to connect users’ online world to their offline physical activities. An essential analysis task is to identify hidden community from these check-ins, i.e., the community not explicitly defined based on the online links in LBSN but implicitly exist in the mobility patterns from these check-ins. The current state-of-the-art systems explore user check-ins to extract the visited venues; analyze the semantic information of the visited venues to model user behaviour patterns; cluster the users with similar patterns into the same community. They assume that users’ check-ins specify the exact venues they visited. However, it has been observed that more than half of users’ check-ins, e.g., in Twitter and Foursquare, are venueless (i.e., exact venues visited are unknown). Motivated by this observation, this work as the first attempt investigates the hidden community detection by exploring all check-ins (i.e., check-ins with/without exact venues). The idea is to identify a list of nearby venues around venueless check-ins. To obtain unfailing regularity even though it is uncertain on which venues have been eventually visited, we develop methods based on the probabilistic venue sequences. By tackling a number of unique technical challenges, the rich and comprehensive information disclosed from all check-ins allows us to uncover communities with high modularity which cannot be achieved by state-of-the-art systems. Empirical study conducted on both real-world and synthetic datasets show the efficiency and effectiveness of our methods.