Recommending Personalized POIs from Location Based Social Network

Location based social networks（ LBSNs） provide location specific data generated from smart phone into online social networks thus people can share their points of interest（ POIs）. POI collections are complex and can be influenced by various factors,such as user preferences,social relationships and geographical influence. Therefore,recommending new locations in LBSNs requires to take all these factors into consideration. However,one problem is how to determine optimal weights of influencing factors in an algorithm in which these factors are combined. The user similarity can be obtained from the user check-in data,or from the user friend information,or based on the different geographical influences on each user＇s check-in activities. In this paper,we propose an algorithm that calculates the user similarity based on check-in records and social relationships,using a proposed weighting function to adjust the weights of these two kinds of similarities based on the geographical distance between users. In addition,a non-parametric density estimation method is applied to predict the unique geographical influence on each user by getting the density probability plot of the distance between every pair of user＇s check-in locations. Experimental results,using foursquare datasets,have shown that comparisons between the proposed algorithm and the other five baseline recommendation algorithms in LBSNs demonstrate that our proposed algorithm is superior in accuracy and recall,furthermore solving the sparsity problem.

An E-Commerce Recommender System Based on Content-Based Filtering

Content-based filtering E-commerce recommender system was discussed fully in this paper. Users＇ unique features can be explored by means of vector space model firstly. Then based on the qualitative value of products informa tion, the recommender lists were obtained. Since the system can adapt to the users＇ feedback automatically, its performance were enhanced comprehensively. Finally the evaluation of the system and the experimental results were presented.

Using DEMATEL for Contextual Learner Modeling in Personalized and Ubiquitous Learning

With the popularity of e-learning,personalization and ubiquity have become important aspects of online learning.To make learning more personalized and ubiquitous,we propose a learner model for a query-based personalized learning recommendation system.Several contextual attributes characterize a learner,but considering all of them is costly for a ubiquitous learning system.In this paper,a set of optimal intrinsic and extrinsic contexts of a learner are identified for learner modeling.A total of 208 students are surveyed.DEMATEL(Decision Making Trial and Evaluation Laboratory)technique is used to establish the validity and importance of the identified contexts and find the interdependency among them.The acquiring methods of these contexts are also defined.On the basis of these contexts,the learner model is designed.A layered architecture is presented for interfacing the learner model with a query-based personalized learning recommendation system.In a ubiquitous learning scenario,the necessary adaptive decisions are identified to make a personalized recommendation to a learner.

Privacy-Preserving Recommendation Based on Kernel Method in Cloud Computing

The application field of the Internet of Things(IoT)involves all aspects,and its application in the fields of industry,agriculture,environment,transportation,logistics,security and other infrastructure has effectively promoted the intelligent development of these aspects.Although the IoT has gradually grown in recent years,there are still many problems that need to be overcome in terms of technology,management,cost,policy,and security.We need to constantly weigh the benefits of trusting IoT products and the risk of leaking private data.To avoid the leakage and loss of various user data,this paper developed a hybrid algorithm of kernel function and random perturbation method based on the algorithm of non-negative matrix factorization,which realizes personalized recommendation and solves the problem of user privacy data protection in the process of personalized recommendation.Compared to non-negative matrix factorization privacy-preserving algorithm,the new algorithm does not need to know the detailed information of the data,only need to know the connection between each data;and the new algorithm can process the data points with negative characteristics.Experiments show that the new algorithm can produce recommendation results with certain accuracy under the premise of preserving users’personal privacy.

Privacy-Preserving Collaborative Filtering Algorithm Based on Local Differential Privacy

Mobile edge computing(MEC)is an emerging technolohgy that extends cloud computing to the edge of a network.MEC has been applied to a variety of services.Specially,MEC can help to reduce network delay and improve the service quality of recommendation systems.In a MEC-based recommendation system,users’rating data are collected and analyzed by the edge servers.If the servers behave dishonestly or break down,users’privacy may be disclosed.To solve this issue,we design a recommendation framework that applies local differential privacy(LDP)to collaborative filtering.In the proposed framework,users’rating data are perturbed to satisfy LDP and then released to the edge servers.The edge servers perform partial computing task by using the perturbed data.The cloud computing center computes the similarity between items by using the computing results generated by edge servers.We propose a data perturbation method to protect user’s original rating values,where the Harmony mechanism is modified so as to preserve the accuracy of similarity computation.And to enhance the protection of privacy,we propose two methods to protect both users’rating values and rating behaviors.Experimental results on real-world data demonstrate that the proposed methods perform better than existing differentially private recommendation methods.

Recommender System Combining Popularity and Novelty Based on One-Mode Projection of Weighted Bipartite Network

Personalized recommendation algorithms,which are effective means to solve information overload,are popular topics in current research.In this paper,a recommender system combining popularity and novelty(RSCPN)based on one-mode projection of weighted bipartite network is proposed.The edge between a user and item is weighted with the item’s rating,and we consider the difference in the ratings of different users for an item to obtain a reasonable method of measuring the similarity between users.RSCPN can be used in the same model for popularity and novelty recommendation by setting different parameter values and analyzing how a change in parameters affects the popularity and novelty of the recommender system.We verify and compare the accuracy,diversity and novelty of the proposed model with those of other models,and results show that RSCPN is feasible.

Time-Aware LSTM Neural Networks for Dynamic Personalized Recommendation on Business Intelligence

Personalized recommendation plays a critical role in providing decision-making support for product and service analysis in the field of business intelligence.Recently,deep neural network-based sequential recommendation models gained considerable attention.However,existing approaches pay litle attention to users'dynamically evolving interests,which are influenced by product attributes,especially product category.To overcome these challenges,we propose a dynamic personalized recommendation model:DynaPR.Specifically,we first embed product information and attribute information into a unified data space.Then,we exploit long short-term memory(LsTM)networks to characterize sequential behavior over multiple time periods and seize evolving interests by hierarchical LSTM networks.Finally,similarity values between users are measured through pairwise interest features,and personalized recommendation lists are generated.A series of experiments reveal the superiority of the proposed method compared withotheradvanced methods.

Integrating Machine Learning and Evidential Reasoning for User Profiling and Recommendation

User profiles representing users’preferences and interests play an important role in many applications of personalized recommendation.With the rapid growth of social platforms,there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation services.The problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources,in different formats and often associated with uncertainty.In this paper,we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and recommendation.The developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach.A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.

PRODUCTS RANKING THROUGH ASPECT-BASED SENTIMENT ANALYSIS OF ONLINE HETEROGENEOUS REVIEWS

With the rapid growth of online shopping platforms, more and more customers intend to share theirshopping experience and product reviews on the Internet. Both large quantity and various forms ofonline reviews bring difficulties for potential consumers to summary all the heterogenous reviews forreference. This paper proposes a new ranking method through online reviews based on differentaspects of the alternative products, which combines both objective and subjective sentiment values.Firstly, weights of these aspects are determined with LDA topic model to calculate the objectivesentiment value of the product. During this process, the realistic meaning of each aspect is alsosummarized. Then, consumers＇ personalized preferences are taken into consideration while calculatingtotal scores of alternative products. Meanwhile, comparative superiority between every two productsalso contributes to their final scores. Therefore, a directed graph model is constructed and the finalscore of each product is computed by improved PageRank algorithm. Finally, a case study is given toillustrate the feasibility and effectiveness of the proposed method. The result demonstrates that whileconsidering only objective sentiment values of the product, the ranking result obtained by our proposedmethod has a strong correlation with the actual sales orders. On the other hand, if consumers expresssubjective preferences towards a certain aspect, the final ranking is also consistent with the actualperformance of alternative products. It provides a new research idea for online customer review miningand personalized recommendation.

Collaborative filtering recommendation algorithm based on interactive data classification

In the matrix factorization(MF)based collaborative filtering recommendation method,the most critical part is to deal with the interaction between the features of users and items.The mainstream approach is to use the inner product for MF to describe the user-item relationship.However,as a shallow model,MF has its limitations in describing the relationship between data.In addition,when the size of the data is large,the performance of MF is often poor due to data sparsity and noise.This paper presents a model called PIDC,short for potential interaction data clustering based deep learning recommendation.First,it uses classifiers to filter and cluster recommended items to solve the problem of sparse training data.Second,it combines MF and multi-layer perceptron(MLP)to optimize the prediction effect,and the limitation of inner product on the model expression ability is eliminated.The proposed model PIDC is tested on two datasets.The experimental results show that compared with the existing benchmark algorithm,the model improved the recommendation effect.

The construction of personalized virtual landslide disaster environments based on knowledge graphs and deep neural networks

Virtual Landslide Disaster environments are important for multilevel simulation,analysis and decision-making about Landslide Disasters.However,in the existing related studies,complex disaster scene objects and relationships are not deeply analyzed,and the scene contents are fixed,which is not conducive to meeting multilevel visualization task requirements for diverse users.To resolve the above issues,a construction method for Personalized Virtual Landslide Disaster Environments Based on Knowledge Graphs and Deep Neural networks is proposed in this paper.The characteristics of relationships among users,scenes and data were first discussed in detail;then,a knowledge graph of virtual Landslide Disaster environments was established to clarify the complex relationships among disaster scene objects,and a Deep Neural network was introduced to mine the user history information and the relationships among object entities in the knowledge graph.Therefore,a personalized Landslide Disaster scene data recommendation mechanism was proposed.Finally,a prototype system was developed,and an experimental analysis was conducted.The experimental results show that the method can be used to recommend intelligently appropriate disaster information and scene data to diverse users.The recommendation accuracy stabilizes above 80%–a level able to effectively support The Construction of Personalized Virtual Landslide Disaster environments.

Trust-Based Personalized Service Recommendation: A Network Perspective

Recent years have witnessed a growing trend of Web services on the Interact. There is a great need of effective service recommendation mechanisms. Existing methods mainly focus on the properties of individual Web services （e.g., func- tional and non-functional properties） but largely ignore users＇ views on services, thus failing to provide personalized service recommendations. In this paper, we study the trust relationships between users and Web services using network modeling and analysis techniques. Based on the findings and the service network model we build, we then propose a collaborative filtering algorithm called Trust-Based Service Recommendation （TSR） to provide personalized service recommendations. This systematic approach for service network modeling and analysis can also be used for other service recommendation studies.

Personalized travel route recommendation using collaborative filtering based on GPS trajectories

Travelling is a critical component of daily life.With new technology,personalized travel route recommendations are possible and have become a new research area.A personalized travel route recommendation refers to plan an optimal travel route between two geographical locations,based on the road networks and users’travel preferences.In this paper,we define users’travel behaviours from their historical Global Positioning System(GPS)trajectories and propose two personalized travel route recommendation methods–collaborative travel route recommendation(CTRR)and an extended version of CTRR(CTRR+).Both methods consider users’personal travel preferences based on their historical GPS trajectories.In this paper,we first estimate users’travel behaviour frequencies by using collaborative filtering technique.A route with the maximum probability of a user’s travel behaviour is then generated based on the naïve Bayes model.The CTRR+method improves the performances of CTRR by taking into account cold start users and integrating distance with the user travel behaviour probability.This paper also conducts some case studies based on a real GPS trajectory data set from Beijing,China.The experimental results show that the proposed CTRR and CTRR+methods achieve better results for travel route recommendations compared with the shortest distance path method.

Region-aware neural graph collaborative filtering for personalized recommendation

Personalized recommender systems have been widely deployed in various scenarios to enhance user experience in response to the challenge of information explosion.Especially,personalized recommendation models based on graph structure have advanced greatly in predicting user preferences.However,geographical region entities that reflect the geographical context of the items is not being utilized in previous works,leaving room for the improvement of personalized recommendation.This study proposes a region-aware neural graph collaborative filtering(RA-NGCF)model,which introduces the geographical regions for improving the prediction of user preference.The approach first characterizes the relationships between items and users with a user-item-region graph.And,a neural network model for the region-aware graph is derived to capture the higher-order interaction among users,items,and regions.Finally,the model fuses region and item vectors to infer user preferences.Experiments on real-world dataset results show that introducing region entities improves the accuracy of personalized recommendations.This study provides a new approach for optimizing personalized recommendation as well as a methodological reference for facilitating geographical regions for optimizing spatial applications.

Multirelationship Aware Personalized Recommendation Model

The existing methods using social information can alleviate the data sparsity issue in collaborative filtering recommendation,but they do not fully tap the complex and diverse user relationships,so it is difficult to obtain an accurate modeling representation of the user.To solve this,we propose a multirelationship aware personalized recommendation(MrAPR)model,which aggregates the various relationships between social users from two aspects of the user’s personal information and interaction sequence.Based on the comprehensive and accurate relationship graphs established,the graph neural network and attention network are used to adaptively distinguish the importance of different relationships and improve the aggregation reliability of multiple relationships.The MrAPR model better describes the characteristics of user interest and can be compatible with the existing sequence recommendation methods.The experimental results on two real-world datasets clearly show the effectiveness of the MrAPR model.

Multi-factor Fusion POI Recommendation Model

In the context of the rapid development of location-based socialnetworks (LBSN), point of interest (POI) recommendation becomes an importantservice in LBSN. The POI recommendation service aims to recommendsome new places that may be of interest to users, help users to better understandtheir cities, and improve users’ experience of the platform. Although the geographicinfluence, similarity of POIs, and user check-ins information have beenused in the existing work recommended by POI, little existing work consideredcombing the aforementioned information. In this paper, we propose to makerecommendations by combing user ratings with the above information. Wemodel four types of information under a unified POI recommendation frameworkand this model is called extended user preference model based on matrixfactorization, referred to as UPEMF. Experiments were conducted on two realworld datasets, and the results show that the proposed method improves theaccuracy of POI recommendations compared to other recent methods.