Personalized Location Recommendation Research Articles

Hybrid-attention and frame difference enhanced network for micro-video venue recognition

Many micro-video related applications, such as personalized location recommendation and micro-video verification, can be benefited greatly from the venue information. Most existing works focus on integrating the information from multi-modal for exact venue category recognition. It is important to make full use of the information from different modalities. However, the performance may be limited by the lacked acoustic modality or textual descriptions in uploaded micro-videos. Therefore, in this paper visual modality is explored as the only modality according to its rich and indispensable semantic information. To this end, a hybrid-attention and frame difference enhanced network (HAFDN) is proposed to generate the comprehensive venue representation. Such network mainly contains two parallel branches: content and motion branches. Specifically, in the content branch, a domain-adaptive CNN model combined with temporal shift module (TSM) is employed to extract discriminative visual features. Then, a novel hybrid attention module (HAM) is introduced to enhance extracted features via three attention mechanisms. In HAM, channel attention, local and global spatial attention mechanisms are used to capture salient visual information from different views. In addition, convolutional Long Short-Term Memory (convLSTM) is enforced after HAM to better encode the long spatial-temporal dependency. A difference-enhanced module parallel with HAM is devised to learn the content variations among adjacent frames, which is usually ignored in prior works. Moreover, in the motion branch, 3D-CNNs and LSTM are used to capture movement variation as a supplement of content branch in a different form. Finally, the features from two branches are fused to generate robust video-level representations for predicting venue categories. Extensive experimental results on public datasets verify the effectiveness of the proposed micro-video venue recognition scheme. The source code is available at https://github.com/hs8945/HAFDN.

Resolving Data Sparsity via Aggregating Graph-Based User–App–Location Association for Location Recommendations

Personalized location recommendations aim to recommend places that users want to visit, which can save their decision-making time in daily life. However, the recommending task faces a serious data sparsity problem because users have only visited a small part of total places in a city. This problem directly leads to the difficulty in learning latent representations of users and locations. In order to tackle the data sparsity problem and make better recommendations, users’ app usage records in different locations are introduced to compensated for both users’ interests and locations’ characteristics in this paper. An attributed graph-based representation model is proposed to dig out user–app–location associations with high-order features aggregated. Extensive experiments prove that better representations of users and locations are obtained by our proposed model, thus it greatly improves location recommendation performances compared with the state-of-art methods. For example, our model achieves 13.20%, 10.1%, and 9.44% higher performance than the state-of-art (SOTA) models in Top3Hitrate, Top3Accuracy, and nDCG3, respectively, in the Telecom dataset. In the TalkingData dataset, our model achieves 9.34%, 13.35%, and 8.56% better performance than the SOTA models in Top2Hitrate, Top2Accuracy, and nDCG2, respectively. Furthermore, numerical results demonstrate that our model can effectively alleviate the data sparsity problem in recommendation systems.

Utilization of Real Time Behavior and Geographical Attraction for Location Recommendation

Personalized location recommendation is an increasingly active topic in recent years, which recommends appropriate locations to users based on their temporal and geospatial visiting patterns. Current location recommendation methods usually estimate the users’ visiting preference probabilities from the historical check-ins in batch. However, in practice, when users’ behaviors are updated in real-time, it is often cost-inhibitive to re-estimate and updates users’ visiting preference using the same batch methods due to the number of check-ins. Moreover, an important nature of users’ movement patterns is that users are more attracted to an area where have dense locations with same categories for conducting specific behaviors. In this paper, we propose a location recommendation method called GeoRTGA by utilizing the real time user behaviors and geographical attractions to tackle the problems. GeoRTGA contains two sub-models: real time behavior recommendation model and attraction-based spatial model. The real time behavior recommendation model aims to recommend real-time possible behaviors which users prefer to visit, and the attraction-based spatial model is built to discover the category-based spatial and individualized spatial patterns based on the geographical information of locations and corresponding location categories and check-in numbers. Experiments are conducted on four public real-world check-in datasets, which show that the proposed GeoRTGA outperforms the five existing location recommendation methods.

A robust personalized location recommendation based on ensemble learning

Recommender systems (RSs) have attracted considerable attention with the aim of optimizing location service efficiency since a large volume of information is generated by location-based social networks. Prediction accuracy is generally considered the main performance evaluation criterion, while the stability of RSs, which might be affected by uncertainty, has rarely been documented. To guarantee the robustness of RSs on the basis of two essential elements, accuracy and stability, this paper proposes an ensemble-based personalized location recommendation (EPLR) algorithm, in which several different categories of individual models are pre-trained to provide a knowledge base, and the accuracy metric in terms of F1 and the information gain (IG) are individually calculated for each user and are used as personalized weights to integrate the individual models. Notably, IG is used as an evaluation index of system stability. To demonstrate and evaluate EPLR in detail, four representative recommendation algorithms, i.e., user-based collaborative filtering (UBCF), singular value decomposition (SVD), friend-based collaborative filtering (FCF) and kernel density estimation (KDE), are selected as individual models for demonstration. Extensive experiments are conducted on two popular datasets: Brightkite and Gowalla. Additionally, three published ensemble recommendation algorithms and four individual models are implemented for comparison. The experimental results show that EPLR outperforms the other considered algorithms in terms of prediction accuracy and exhibits a promising advantage in system stability.

STS: Spatial–Temporal–Semantic Personalized Location Recommendation

The rapidly growing location-based social network (LBSN) has become a promising platform for studying users’ mobility patterns. Many online applications can be built based on such studies, among which, recommending locations is of particular interest. Previous studies have shown the importance of spatial and temporal influences on location recommendation; however, most existing approaches build a universal spatial–temporal model for all users despite the fact that users always demonstrate heterogeneous check-in behavior patterns. In order to realize truly personalized location recommendations, we propose a Gaussian process based model for each user to systematically and non-linearly combine temporal and spatial information to predict the user’s displacement from their currently checked-in location to the next one. The locations whose distances to the user’s current checked-in location are the closest to the predicted displacement are recommended. We also propose an enhancement to take into account category information of locations for semantic-aware recommendation. A unified recommendation framework called spatial–temporal–semantic (STS) is introduced to combine displacement prediction and the semantic-aware enhancement to provide final top-N recommendation. Extensive experiments over real datasets show that the proposed STS framework significantly outperforms the state-of-the-art location recommendation models in terms of precision and mean reciprocal rank (MRR).

Hybrid-Attention Enhanced Two-Stream Fusion Network for Video Venue Prediction

Video venue category prediction has been drawing more attention in the multimedia community for various applications such as personalized location recommendation and video verification. Most of existing works resort to the information from either multiple modalities or other platforms for strengthening video representations. However, noisy acoustic information, sparse textual descriptions and incompatible cross-platform data could limit the performance gain and reduce the universality of the model. Therefore, we focus on discriminative visual feature extraction from videos by introducing a hybrid-attention structure. Particularly, we propose a novel Global-Local Attention Module (GLAM), which can be inserted to neural networks to generate enhanced visual features from video content. In GLAM, the Global Attention (GA) is used to catch contextual scene-oriented information via assigning channels with various weights while the Local Attention (LA) is employed to learn salient object-oriented features via allocating different weights for spatial regions. Moreover, GLAM can be extended to ones with multiple GAs and LAs for further visual enhancement. These two types of features respectively captured by GAs and LAs are integrated via convolution layers, and then delivered into convolutional Long Short-Term Memory (convLSTM) to generate spatial-temporal representations, constituting the content stream. In addition, video motions are explored to learn long-term movement variations, which also contributes to video venue prediction. The content and motion stream constitute our proposed Hybrid-Attention Enhanced Two-Stream Fusion Network (HA-TSFN). HA-TSFN finally merges the features from two streams for comprehensive representations. Extensive experiments demonstrate that our method achieves the state-of-the-art performance in the large-scale dataset Vine. The visualization also shows that the proposed GLAM can capture complementary scene-oriented and object-oriented visual features from videos. Our code is available at: https://github.com/zhangyanchao1014/HA-TSFN .

Personalized location recommendation by fusing sentimental and spatial context

Internet users would like to obtain interesting location information for a travel. With the rapid development of social media, many kinds of location recommender systems are proposed in recent years. Existing methods mostly focus on mining user check-in information that could be leveraged to understand their trajectories. However, the characteristics and attributes of geographical locations also play an important role in recommender systems. In this paper, sentimental attributes of locations are explored and we propose a Point of Interest (POI) mining method and a personalized recommendation model by fusing sentimental spatial context. First, a Sentimental–Spatial POI Mining (SPM) method is utilized to mine the POIs by fusing the sentimental and geographical attributes of locations. Second, we recommend the POIs to users by a Sentimental–Spatial POI Recommendation (SPR) model incorporating the factors of sentiment similarity and geographical distance. Last, the advantages and superior performance of our methods are demonstrated by extensive experiments on a real-world dataset.

A Personalized Location Recommendation System based on Probability and Proximity

Big data is an emerging field plays a valuable role in the extraction of information from raw data. It has found its applications in areas such as predictive analytics, healthcare analytics, financial analytics, and retail analytics and so on. The enormous growth of the Internet has become a source for availability of the huge volume of data online. It is difficult to find out the necessary information from huge data within a short period. The availability of enormous data craves the need of an information filtering system and this information filtering systems are capable of providing the required data to users. The rapid growth of big data lays the path to recommendation systems. A recommendation system is an information filtering tool which has more impacts in day to day life of everyone and also redefines our lives. Recommendation systems provide suggestions based on user preferences, requirements, and interests. The reviews and rating values given by people are used to answer similar interest queries with predictions and suggestions. Reviews and Feedback play a key role in the decision-making process. People share their experiences in the form of feedback, ratings, and reviews and so on. If a user wants to visit a location and if he does not have prior knowledge of it, then he may use reviews and feedback given by others who visited the location already. It is not possible for a user to go through huge volumes of reviews and sometimes it may mislead the user to take wrong decisions if he goes by the review given by a person with a contrasting taste. In such cases, Recommendation systems are needed, which helps users in the decision-making process. In most of the existing methods, they used Point of Interest (POI) of users to recommend the locations. The main objective is to develop a Personalized Location Recommendation System, which will recommend the locations to users using Probability and Proximity. Our model uses Probability and Proximity measures to recommend the locations.

Combining Location2Vec with LSTM to predict next locations from trajectory data

Abstract. Research on human location prediction is beneficial personalized location recommendations, location-based advertising, and ride-sharing services. The prediction of future locations is generally based on historical trajectory data. With the development and prevalence of mobile sensors, large volumes of data that can capture human trajectories are generated and provide researchers with more adequate and accurate data to study human trajectories and location predictions. In this paper, we propose a model containing long short-term memory (LSTM) to understand historical trajectories and predict future locations. LSTM is a special recurrent neural network (RNN) architecture that contains three gates and one internal state to control the storage of information. Additionally, we leverage the LINE (Large-scale Information Network Embedding), an embedding method to transform vertices into large scale networks, to transform locations into spatial vectors according to their distance information, which we name it “Location2Vec”. By feeding the summation of the dynamic location embeddings and pre-trained Location2Vec embeddings into LSTM model, it can effectively predict next locations of a trajectory and improve the predicting accuracy. Finally, we verify the reliability of the model, and the results show that our model outperforms other traditional trajectory models.

Personalized location recommendation using mobile phone usage information

Location recommendation has become a hot research area in recent years. The cold-start problem is still a great challenge in personalized location recommendation, which makes it difficult to infer a new user’s preferences, because a new user generally has never visited any location at the start. To address this problem, the existing studies usually exploit other information, e.g., demographic features, to characterize users. However, such little information is not sufficient to profile users accurately. In addition, abundant mobile phone usage information can be recorded when users are using their phones, e.g., the use frequency of Apps, which can fully reveal the diverse characteristics of different users. In this paper, we propose a personalized location recommendation method using mobile phone usage information, which transforms the location recommendation problem into a regression task, and extracts six types of mobile phone usage features to profile users. Demographic features and location features are also extracted. To efficiently reduce model parameters, factorization machines are employed to construct the recommendation model, which models feature interactions as the inner products of latent vectors with matrix factorization. We evaluate the proposed method using the open dataset of Nokia Mobile Data Challenge, and experimental results show the effectiveness of the proposed method in personalized location recommendation.

From Fingerprint to Footprint

With increasing diversity of user interest and preference, personalized location recommendation is essential and beneficial to our daily life. To achieve this, the most critical challenge is the cold-start recommendation problem, for we cannot learn preference from cold-start users without any historical records. In this paper, we demonstrate that it is feasible to make personalized location recommendation by learning user interest and location features from app usage data. By proposing a novel generative model to transfer user interests from app usage behavior to location preference, we achieve personalized location recommendation via learning the interest's correlation between locations and apps. Based on two real-world datasets, we evaluate our method's performance with a variety of scenarios and parameters. The results demonstrate that our method outperforms the state-of-the-art solutions in solving cold-start problem, i.e., when there are 60% cold-start users, we can still achieve a 77.0% hitrate in recommending the top five locations, which is at least 9.6% higher than the baselines. Our study is the first step forward for transferring user interests learning from online fingerprints to offline footprints, which paves the way for better personalized location recommendation services.

Personalized Location Recommendation System Personalized Location Recommendation System

Location acquisition and wireless communication technologies are growing in location-based social networks. With the rapid development of location-based social networks (LBSNs), location recommendation has become an important for helping users to discover interesting locations. Most current studies on spatial item recommendations do not consider the sequential influence of locations. The authors proposed a personalized location recommendation system as a probabilistic generative model that aims to mimic the process of human decision-making when visiting locations. In this system, three tasks are involved, such as: extracting user's personal interests; extracting sequential influence; and combining them into unified networks. This system utilizes data collected from LBSNs to model a user's behavior and locations with real datasets, and it determines a user's preferred locations using collaborative filtering and a Locality Sensitive Hashing (ALSH) technique. It overcomes the challenges of the user's check-in data in LBSNs having a low sampling rate in both space and time and a huge prediction space.

A two-step personalized location recommendation based on multi-objective immune algorithm

The increasing number of users participating in location-based social networks has resulted in an information overload problem. Recommendation is a process that can free users from this dilemma. Most algorithms either ignore geographical and social properties, or require a tunable coefficient to determine the effect of each property on the outcome. Simultaneously combining these properties has proven to be a challenge. In this paper, we propose a two-step personalized location recommendation that is based on a multi-objective immune algorithm. It can simultaneously optimize the matching qualities of similarity and geographic properties as two functions, thereby providing location recommendations by improving one desired objective without detracting from the other. In the process, each list provides a different compromise between the similarity of check-in preferences and the geographical influence of the user. The user is offered choices from a set of lists that are compiled from the individual’s selection of the various tradeoffs. The advantage of this algorithm is that it can recommend user lists without the need to tune any of the weighting coefficients. Experiments performed using the actual data demonstrated that the proposed algorithm is promising and is an effective means for providing accurate recommendations for a user’s desired location.

Decision Tree-Based Contextual Location Prediction from Mobile Device Logs

Contextual location prediction is an important topic in the field of personalized location recommendation in LBS (location-based services). With the advancement of mobile positioning techniques and various sensors embedded in smartphones, it is convenient to obtain massive human mobile trajectories and to derive a large amount of valuable information from geospatial big data. Extracting and recognizing personally interesting places and predicting next semantic location become a research hot spot in LBS. In this paper, we proposed an approach to predict next personally semantic place with historical visiting patterns derived from mobile device logs. To address the problems of location imprecision and lack of semantic information, a modified trip-identify method is employed to extract key visit points from GPS trajectories to a more accurate extent while semantic information are added through stay point detection and semantic places recognition. At last, a decision tree model is adopted to explore the spatial, temporal, and sequential features in contextual location prediction. To validate the effectiveness of our approach, experiments were conducted based on a trajectory collection in Guangzhou downtown area. The results verified the feasibility of our approach on contextual location prediction from continuous mobile devices logs.

Personalized location recommendation by aggregating multiple recommenders in diversity

Location recommendation is an important feature of social network applications and location-based services. Most existing studies focus on developing one single method or model for all users. By analyzing data from two real location-based social networks (Foursquare and Gowalla), in this paper we reveal that the decisions of users on place visits depend on multiple factors, and different users may be affected differently by these factors. We design a location recommendation framework that combines results from various recommenders that consider different factors. Our framework estimates, for each individual user, the underlying influence of each factor to her. Based on the estimation, we aggregate suggestions from different recommenders to derive personalized recommendations. Experiments on Foursquare and Gowalla show that our proposed method outperforms the state-of-the-art methods on location recommendation.

STCAPLRS

Newly emerging location-based social media network services (LBSMNS) provide valuable resources to understand users’ behaviors based on their location histories. The location-based behaviors of a user are generally influenced by both user intrinsic interest and the location preference, and moreover are spatial-temporal context dependent. In this article, we propose a spatial-temporal context-aware personalized location recommendation system (STCAPLRS), which offers a particular user a set of location items such as points of interest or venues (e.g., restaurants and shopping malls) within a geospatial range by considering personal interest, local preference, and spatial-temporal context influence. STCAPLRS can make accurate recommendation and facilitate people’s local visiting and new location exploration by exploiting the context information of user behavior, associations between users and location items, and the location and content information of location items. Specifically, STCAPLRS consists of two components: offline modeling and online recommendation. The core module of the offline modeling part is a context-aware regression mixture model that is designed to model the location-based user behaviors in LBSMNS to learn the interest of each individual user, the local preference of each individual location, and the context-aware influence factors. The online recommendation part takes a querying user along with the corresponding querying spatial-temporal context as input and automatically combines the learned interest of the querying user, the local preference of the querying location, and the context-aware influence factor to produce the top- k recommendations. We evaluate the performance of STCAPLRS on two real-world datasets: Dianping and Foursquare. The results demonstrate the superiority of STCAPLRS in recommending location items for users in terms of both effectiveness and efficiency. Moreover, the experimental analysis results also illustrate the excellent interpretability of STCAPLRS.

An Enhanced Travel Package Recommendation System based on Location Dependent Social Data

Location based social networking systems add location as main dimension to the social connections which gives necessities for personalized location recommendations. Travel packages can be personalized by obtaining user preferences, POI attractions and patterns between them from LBSNs. Existing recommendation systems concentrate mostly either recommending locations , travel packages to a single user or not precise enough, just recommending a list of possibly suitable packages to select by a user group. In our system travel packages are personalized to a user group by considering their common interests, social connections among them along with their individual interests, constraints. Recommendations made precise by considering multiple metrics which varies in degree of personalization and time period of evaluation. We built a prototype system and evaluated results based on data obtained from foursquare site. Experimental results prove system recommends effectively in single user scenario and also adapted well to user group scenario.