Location-based Recommendation Research Articles

Collaborative filtering by graph convolution network in location-based recommendation system

Collaborative filtering by graph convolution network in location-based recommendation system

Hostel Finder: Location-Based Recommendation System for Hostels and PGS with Transit Information

Hostel Finder: Location-Based Recommendation System for Hostels and PGS with Transit Information

A Critical Review on Location Based Hybrid Filtering Recommender Systems

A recommender system is basically a type of information filtering system that suggests/recommends items based on the factors that constitute what the user is most interested in. The recommendations are typically provided in relation to different decision-making processes. Tourism is a social phenomenon where people deliberately travel in search of recreation, well-being, cultural exploration or get themselves softened up. But, the amount of information available online keeps expanding at exponential rates and thus the users have expressed their feeling of frustration at how challenging it is to find the appropriate information. This problem is called information overload. This is where the recommendation system comes into play which helps in solving the information overload problem. The hybrid system addresses the disadvantages where location-based recommendation systems are used individually, of which the most notable is the cold start issue. Furthermore, in order to improve the accuracy of the prediction to recommend items, these systems search for the ideal fusion of different approaches. Thus, the hybrid recommendation method solves the challenges like ‘cold start problem’, inability to capture changes in user behavior, sparsity and selecting correct choices for users. This paper explores the hybrid recommendation systems and other filtering techniques used in various fields, their challenges, how they can also be used for tourism recommender systems based on the longitudes and latitudes.

Relevancy or Diversity?

Reading information in news feed apps has become a kind of popular content consumption in recent years. However, there are contradictory conclusions about the recommendation strategies. Although some previous research has studied the algorithms to improve the accuracy of the combined of relevancy and diversity strategies, how to compromise them according to user attitude and behavior from individual level is limited. This study aims to solve the dilemma at a theoretical level, and the authors find that the degree of multi-context use is a key boundary. Specifically, 1) the location-based recommendation method may lose effectiveness when the degree of a multi-context is high. 2) The users who prefer to use news feed systems in various contexts in their daily life are more likely to read diverse information. The authors suppose that with the increase of the degree of multi-context use, the location-based recommendation may trigger users perceived privacy threat, which will reduce their satisfaction and participation intention.

A Naïve Bayes prediction model on location-based recommendation by integrating multi-dimensional contextual information

A Naïve Bayes prediction model on location-based recommendation by integrating multi-dimensional contextual information

Community detection of trajectory data for location-based facility recommendation system

Community detection of trajectory data for location-based facility recommendation system

Personal Privacy Data Protection in Location Recommendation System

At present, there are many location-based recommendation algorithms and systems, including location calculation, route calculation, and so on. However, in the general information data publishing, the privacy issues in the published data have not been fully paid attention to and protected. The purpose of this article is to investigate the effectiveness of personal privacy data protection in location recommendation systems. This paper first introduces the basis and importance of research on data security and secrecy, analyses personal privacy issues in data publishing in the era of big data, summarizes the research status in the field of security and secrecy at home and abroad, and introduces the process of data security and the role of users in it. Then, some classic privacy security modules in this field are introduced, and the privacy of data storage security concepts in the current situation mentioned in this paper is analyzed. A geographic location-based privacy protection scheme in mobile cloud is proposed. Privacy analysis, sensitive attribute generalization information analysis, route synthesis analysis and related experiments are performed on the location recommendation system. The experimental results show that the scheme proposed in this paper is more secure and has less loss of data availability.

A deep learning based approach for trajectory estimation using geographically clustered data

This study presents a novel approach to predict a complete source to destination trajectory of a vehicle using a partial trajectory query. The proposed architecture is scalable to extremely large-scale data with respect to the dense road network. A deep learning model Long Short Term Memory (LSTM) has been used for analyzing the temporal data and predicting the complete trajectory. To handle a large amount of data, clustering of similar trajectory data is used that helps in reducing the search space. The clusters based on geographical locations and temporal values are used for training different LSTM models. The proposed approach is compared with the other published work on the parameters as Average distance error and one step prediction accuracy The one-step prediction accuracy is as good as 81% and Distance error are .33 Km. Our proposed approach termed Clustered LSTM is outperforming in both the parameters when compared with other reported results. The proposed solution is a clustering-based predictive model that effectively contributes to accurately handle the large scale data. The outcome of this study leads to improvise the navigation systems, route prediction, traffic management, and location-based recommendation systems.

Lamps: Location-Aware Moving Top-k Pub/Sub

Huge amounts of spatio-textual objects, such as geo-tagged tweets, are being generated at an unprecedented scale, leading to a variety of applications such as location-based recommendation and sponsored search. Many of these applications need to support moving top-k spatio-textual subscriptions. For example, while walking, a tourist issues a moving subscription and looks for top-k advertisements published by nearby shops. Unfortunately, existing methods that monitor the results of spatio-textual subscriptions support only static top-k subscriptions or moving boolean subscriptions. In this article, we propose a novel system, called Lamps (Location-Aware Moving Top-k Pub/Sub), which continuously monitors the top-k most relevant spatio-textual objects for a large number of moving top-k spatio-textual subscriptions simultaneously. To the best of our knowledge, this is the first study of a location-aware moving top-k pub/sub system. As with existing works on continuous moving top-k subscription processing, Lamps employs the concept of a safe region to monitor top-k results. However, unlike with existing works that assume static objects, top-k result updates may be triggered by newly generated objects. To continuously monitor the top-k results for massive moving subscriptions efficiently, we propose SQ-tree, a novel index based on safe regions, to filter subscriptions whose top-k results do not change. Moreover, to reduce the expensive cost of safe region re-evaluation, we develop a novel approximation technique for safe region construction. Our experimental results on real datasets show that Lamps achieves higher performance than baseline approaches.

Deep Representation Learning for Location-Based Recommendation

Location-based recommendation has recently received a lot of attention in the communities of information service and mobile application. Its task is to provide personalized recommendations of points of interest (POIs) to users at a certain time and location. However, existing location-based recommendation models have at least two main drawbacks: first they cannot adequately capture semantic features of POIs and users, which may lead to unsatisfactory recommendations and second they cannot effectively address the cold-start problem. To address the above drawbacks, in this article, we first propose a novel deep representation learning-based model (DRLM) for improving the recommendation accuracy. In DRLM, we mainly focus on learning to accurately represent semantic features of POIs and users. Specifically, four co-occurrence matrices are constructed to produce four different original features for each POI, and a principal component analysis (PCA) algorithm is utilized to generate a semantic feature of each POI from its four original features. On the other hand, a three-modal simple recurrent unit (TMSRU) network is given to constructed semantic features of users using semantic features of POIs, times, and locations. We further propose minimum description length (MDL)-based and skyline-based strategies to address the cold-start issues for new users and new POIs, respectively. Through experiments on two real-world data sets, we show that compared with the state-of-the-art approaches, the proposed model DRLM can achieve the superior performance in terms of high recommendation accuracy and effectiveness in handling the cold-start problem.

Linked Open Data in Location-Based Recommendation System on Tourism Domain: A Survey

Linked open data is a relatively new topic area with great potential in a wide range of fields. In the tourism domain, many studies are using linked open data to address the problem of location-based recommendation by integrating data with other linked open datasets to enrich data and tourism content for reacting to the needs of tourists. This work aims not only to present a systematic review and mapping of the linked open data in location-based recommendation system on tourism domain, but also to provide an overview of the current research status in the area. First, we classify journal papers in this area from 2001 to 2018 by the year of publication. Second, we analyze and categorize journal papers by the different recommendation applications including problem formulations, data collections, proposed algorithms/systems, and experimental results. Third, we group the linked open data sources used in location-based recommendation system on tourism. Next, we summarize the research achievements and present the distribution of the different categories of location-based recommendation applications via linked open data. Last, we also guide the possible future research direction for the linked open data in location-based recommendations on tourism.

Location recommendation privacy protection method based on location sensitivity division

Location-based recommendation services can provide users with convenient services, but this requires monitoring and collecting a large amount of location information. In order to prevent location information from being leaked after monitoring and collection, location privacy must be effectively protected. Therefore, this paper proposes a privacy protection method based on location sensitivity for location recommendation. This method uses location trajectories and check-in frequencies to set a threshold so as to classify location sensitivity levels. The corresponding privacy budget is then assigned based on the sensitivity to add Laplace noise that satisfies the differential privacy. Experimental results show that this method can effectively protect the user’s location privacy and reduce the impact of differential privacy noise on service quality.

Multi-objective optimization for location-based and preferences-aware recommendation

Location is of vital importance in recommender systems. This paper proposes a novel multi-objective framework for location-based and preference-aware recommendation. Under this framework, location-based recommendation is modeled as a multiobjective optimization problem and two contradictory objective functions are taken into consideration. One objective function aims to depict the performance of recommendation algorithm to recommend similar items. Another objective function reflects the ability of recommendation algorithm to recommend diverse items. It is a challenge to optimize these two contradictory objective functions simultaneously. In this paper, a novel multi-objective evolutionary algorithm is proposed to solve this modeled multiobjective optimization problem. The proposed algorithm can return a series of high-quality recommendation candidate solutions in one run and every solution is a trade-off between these two objective functions. The proposed algorithm is applied on two real recommendation scenarios: movie recommendation and music recommendation. Experimental results show that the proposed algorithm can produce recommendation solutions which are much better than those produced by existing algorithms in location-based recommendation and the proposed algorithm also has great performance in alleviating data sparsity and cold-start problems.

Location and Trajectory Identification from Microblogs

The rapid development of social networks has resulted in a proliferation of user-generated content (UGC), which can benefit many applications. In this paper, we study the problem of identifying a user’s locations from microblogs, to facilitate effective location-based advertisement and recommendation. Since the location information in a microblog is incomplete, we cannot get an accurate location from a local microblog. As such, we propose a global location identification method, Glitter. Glitter combines multiple microblogs of a user and utilizes them to identify the user’s locations. Glitter not only improves the quality of identifying a user’s location but also supplements the location of a microblog so as to obtain an accurate location of a microblog. To facilitate location identification, Glitter organizes points of interest (POIs) into a tree structure where leaf nodes are POIs and non-leaf nodes are segments of POIs, e.g., countries, cities, and streets. Using the tree structure, Glitter first extracts candidate locations from each microblog of a user which correspond to some tree nodes. Then Glitter aggregates these candidate locations and identifies top-k locations of the user. Using the identified top-k user locations, Glitter refines the candidate locations and computes top-k locations of each microblog. To achieve high recall, we enable fuzzy matching between locations and microblogs. We propose an incremental algorithm to support dynamic updates of microblogs. We also study how to identify users’ trajectories based on the extracted locations. We propose an effective algorithm to extract high-quality trajectories. Experimental results on real-world datasets show that our method achieves high quality and good performance, and scales well.

Mobile marketing recommendation method based on user location feedback

Location-based mobile marketing recommendation has become one of the hot spots in e-commerce. The current mobile marketing recommendation system only treats location information as a recommended attribute, which weakens the role of users and shopping location information in the recommendation. This paper focuses on location feedback data of user and proposes a location-based mobile marketing recommendation model by convolutional neural network (LBCNN). First, the users’ location-based behaviors are divided into different time windows. For each window, the extractor achieves users’ timing preference characteristics from different dimensions. Next, we use the convolutional model in the convolutional neural network model to train a classifier. The experimental results show that the model proposed in this paper is better than the traditional recommendation models in the terms of accuracy rate and recall rate, both of which increase nearly 10%.

Achieving High Privacy Protection in Location-based Recommendation Systems

In recent years, privacy has become great attention in the research community. In Location-based Recommendation Systems (LbRSs), the user is constrained to build queries depend on his actual position to search for the closest points of interest (POIs). An external attacker can analyze the sent queries or track the actual position of the LbRS user to reveal his\her personal information. Consequently, ensuring high privacy protection (which is including location privacy and query privacy) is a fundamental thing. In this paper, we propose a model that guarantees high privacy protection for LbRS users. The model is work by three components: The first component (selector) uses a new location privacy protection approach, namely, the smart dummy selection (SDS) approach. The SDS approach generates a strong dummy position that has high resistance versus a semantic position attack. The second component (encryptor) uses an encryption-based approach that guarantees a high level of query privacy versus a sampling query attack. The last component (constructor) constructs the protected query that is sent to the LbRS server. Our proposed model is supported by a checkpoint technique to ensure a high availability quality attribute. Our proposed model yields competitive results compared to similar models under various privacy and performance metrics.

Enabling Smart Anonymity Scheme for Security Collaborative Enhancement in Location-Based Services

Security enhancement is and always will be a prime concern for the deployment of point-of-interest (POI) recommendation services in mobile sensing environment. Recent tamper-proof technical protection such as strong encryption has undoubtedly become a major safeguard against threats to privacy in location-based services. Although the disclosure of location information could increase recommendation accuracy, the publication of trajectory data to untrusted entities could reveal sensitive details, e.g., daily routes, destinations, and favorite restaurants. In this paper, we propose a smart scheme named BUSA to approach the above problem by reconciling the tension between privacy protection and recommendation accuracy in location-based recommendation services. This scheme uses anonymizer agents positioned between the service-requesting users and location service providers; these agents operate by dividing the query information and using k -anonymity to enhance privacy protection. The scheme also utilizes clustering techniques to group users into clusters by learning their trajectory data and selects the spatial center cells as a cluster core and a benchmark for calculating recommendations via trust computing. An anonymizer coordination strategy is proposed to replace a low-performing anonymizer with one that provides stronger privacy protection for a recommendation service. The BUSA scheme adopts k-anonymity and clustering to protect privacy, and the calculated recommendation will be suitable for the cluster core that represents the entirety of users' location preferences. The security analysis reveals that the BUSA scheme can effectively protect privacy against fraudulent query requestors and the simulation results also indicate that it provides stronger privacy protection than its counterparts from the perspective of recommendation hit rate and the extent of disclosure.

A single quadtree-based algorithm for top-[formula omitted] spatial keyword query

Recent years have witnessed the generation of a massive amount of spatial–textual data. In view of this, a new type of query coined spatial keyword query has been proposed to deal with the location-based services with additional keyword constraint. This paper studies one of the most popular spatial keyword queries called Top-k Spatial Keyword Query(TkSKQ). Explicitly speaking, given a set of objects, a TkSKQ finds the k objects that are closest to the querier with each of these k objects satisfying all the keywords specified by the query. This kind of query is of paramount importance in a variety of application domains such as location-based recommendation and advertisement.The state-of-art algorithm for processing a TkSKQ is highly sensitive to the number of query keywords specified in the query such that its performance degrades significantly with an increase in the number of keywords. To remedy this drawback, this paper proposes a novel mechanism that utilizes an additional keyword list to enhance the efficiency of the existing solution. Based on this indexing technique, our algorithm needs only traverse a single quadtree when processing a TkSKQ. Moreover, we study how to prioritize the keywords in the vocabulary so as to optimize the performance of our technique. Furthermore, we deal with a generalized version of the TkSKQ problem, called HkSKQ. A similar technique can also be useful for solving HkSKQ. Experimental results on both synthetic and real data reveal the superiority of our proposed scheme.

A comparative study of location-based recommendation systems

AbstractRecent advancements in location-based recommendation system (LBRS) and the availability of online applications, such as Twitter, Instagram, Foursquare, Path, and Facebook have introduced new research challenges in the area of LBRS. Use of content, such as geo-tagged media, point location-based, and trajectory-based information help in connecting the gap between the online social networking services and the physical world. In this article, we present a systematic review of the scientific literature of LBRS and summarize the efforts and contributions proposed in the literature. We have performed a qualitative comparison of the existing techniques used in the area of LBRS. We present the basic filtration techniques used in LBRS followed by a discussion on the services and the location features the LBRS utilizes to perform the recommendations. The classification of criteria for recommendations and evaluation metrics are also presented. We have critically investigated the techniques proposed in the literature for LBRS and extracted the challenges and promising research topics for future work.

Aggregating social media data with temporal and environmental context for recommendation in a mobile tour guide system

Purpose Manufacturers of smartphone devices are increasingly utilising a diverse range of sensors. This innovation has enabled developers to accurately determine a user’s current context. One area that has been significantly enhanced by the increased use of context in mobile applications is tourism. Traditionally, tour guide applications rely heavily on location and essentially ignore other types of context. This has led to problems of inappropriate suggestions and tourists experiencing information overload. These problems can be mitigated if appropriate personalisation and content filtering is performed. This research proposes an intelligent context-aware recommender system that aims to minimise the highlighted problems. Design/methodology/approach Intelligent reasoning was performed to determine the weight or importance of different types of environmental and temporal context. Environmental context such as the weather outside can have an impact on the suitability of tourist attractions. Temporal context can be the time of day or season; this is particularly important in tourism as it is largely a seasonal activity. Social context such as social media can potentially provide an indication of the “mood” of an attraction. These types of contexts are combined with location data and the context of the user to provide a more effective recommendation to tourists. The evaluation of the system is a user study that utilised both qualitative and quantitative methods, involving 40 participants of differing gender, age group, number of children and marital status. Findings This study revealed that the participants selected the context-based recommendation at a significantly higher level than either location-based recommendation or random recommendation. It was clear from analysing the questionnaire results that location is not the only influencing factor when deciding on a tourist attraction to visit. Research limitations/implications To effectively determine the success of the recommender system, various combinations of contextual conditions were simulated. Simulating contexts provided the ability to randomly assign different contextual conditions to ensure an effective recommendation under all circumstances. This is not a reflection of the “real world”, because in a “real world” field study the majority of the contextual conditions will be similar. For example, if a tourist visited numerous attractions in one day, then it is likely that the weather conditions would be the same for the majority of the day, especially in the summer season. Practical implications Utilising this type of recommender system would allow the tourists to “go their own way” rather than following a prescribed route. By using this system, tourists can co-create their own experience using both social media and mobile technology. This increases the need to retain user preferences and have it available for multiple destinations. The application will be able to learn further through multiple trips, and as a result, the personalisation aspect will be incrementally refined over time. This extensible aspect is increasingly important as personalisation is gradually more effective as more data is collated. Originality/value This paper contributes to the body of knowledge that currently exists regarding the study of utilising contextual conditions in mobile recommender systems. The novelty of the system proposed by this research is the combination of various types of temporal, environmental and personal context data to inform a recommendation in an extensible tourism application. Also, performing sentiment analysis on social media data has not previously been integrated into a tourist recommender system. The evaluation concludes that this research provides clear evidence for the benefits of combining social media data with environmental and temporal context to provide an effective recommendation.