Collaborative Recommendation Method Research Articles

Collaborative Recommendation Method Based on Community Co-Clustering in Location Based Social Networks

Collaborative Recommendation Method Based on Community Co-Clustering in Location Based Social Networks

Document recommendation based on interests of co-authors for brain science.

Personalized knowledge recommendation is an effective measure to provide individual information services in the field of brain science. It is essential that a complete understanding of authors' interests and accurate recommendation are carried out to achieve this goal. In this paper, a collaborative recommendation method based on co-authorship is proposed to make. In our approach, analysis of collaborators' interests and the calculation of collaborative value are used for recommendations. Finally, the experiments using real documents associated with brain science are given and provide supports for collaborative document recommendation in the field of brain science.

Research on Rating Error and Quality Metrics for Collaborative Filtering Recommendation Methods

The collaborative filtering recommendation system has been widely used in E-commerce as a relatively successful recommendation system. At present, the focus of collaborative filtering recommendation research is mainly on how to improve the accuracy of recommendation by improving the recommendation algorithm. However, in real world, the user’s rating behaviour is not perfectly rational. It is no odd that there is deviation of rating to any a given item for a user in real evaluation. In this case, what it means for the improvement of collaborative filtering recommendation methods, and how they performed when we use the commonly used quality metrics to evaluate the collaborative filtering recommendation methods? In view of these problems, this paper presupposes that the user’s rating behaviour is a bounded rational behaviour, and based on the normality hypothesis of rating error, introduces a simulated rating experiment innovatively to analyse the effect that rating prediction can achieve in sense of the commonly used quality metrics. This study is of significance for the research and application of collaborative filtering recommendation technology.

Temporal‐aware and sparsity‐tolerant hybrid collaborative recommendation method with privacy preservation

SummaryWith the explosive growth of cloud services, how to design effective recommendation models has become more and more important. Temporal information has been proved to be an important factor affecting recommendation performance. Actually, both of user behaviors and QoS performance of services are time‐sensitive, especially in dynamic cloud environment. However, most existing collaborative recommendation methods seldom consider temporal influence to QoS performance. Furthermore, with the ever‐increasing number of security threats in clouds, privacy preservation becomes an important problem to be addressed in recommender systems. Based on these observations, in this paper, we propose a temporal‐aware and sparsity‐tolerant hybrid collaborative recommendation method with privacy preservation, where tensor factorization‐based CF model is integrated into neighborhood‐based CF model to achieve improved recommendation performance. Specifically, temporal influence is considered into recommendation model by distinguishing short‐term QoS metrics from long‐term QoS metrics. A privacy‐aware time aggregation mechanism is adopted to preserve the sensitive time information of users. Moreover, to deal with the sparsity problem, a sparsity‐oriented data QoS rating prediction mechanism based on tensor factorization technique is applied to predict the missing or unrated QoS rating data. Finally, predictions are made based on both stable and temporal nearest neighbors. Experiments are conducted to demonstrate the prediction performance of our proposal.

Leveraging Kernel-Incorporated Matrix Factorization for App Recommendation

The ever-increasing number of smartphone applications (apps) available on different app markets poses a challenge for personalized app recommendation. Conventional collaborative filtering-based recommendation methods suffer from sparse and binary user-app implicit feedback, which results in poor performance in discriminating user-app preferences. In this article, we first propose two kernel incorporated probabilistic matrix factorization models, which introduce app-categorical information to constrain the user and app latent features to be similar to their neighbors in the latent space. The two models are solved by Stochastic Gradient Descent with a user-oriented negative sampling scheme. To further improve the recommendation performance, we construct pseudo user-app ratings based on user-app usage information, and propose a novel kernelized non-negative matrix factorization by incorporating non-negative constraints on latent factors to predict user-app preferences. This model also leverages user--user and app--app similarities with regard to app-categorical information to mine the latent geometric structure in the pseudo-rating space. Adopting the Karush--Kuhn--Tucker conditions, a Multiplicative Updating Rules based optimization is proposed for model learning, and the convergence is proved by introducing an auxiliary function. The experimental results on a real user-app installation usage dataset show the comparable performance of our models with the state-of-the-art baselines in terms of two ranking-oriented evaluation metrics.

User-based collaborative filtering recommendation method combining with privacy concerns intensity in mobile commerce

The existing personalised recommender system gives little consideration to users' privacy concerns in mobile commerce. In order to address this issue and some other shortcomings in item recommendations, the paper proposes a novel user-based collaborative filtering recommendation method combining with privacy concerns intensity and introduces the users' six dimensions privacy concerns factors, such as privacy tendency, internal control point, openness, extroversion, agreeableness, and social group influence. The paper puts forward the metric method of privacy concerns intensity with these privacy concerns influence factors, which are used to obtain the similarity preference of users for collective filtering recommendation. Experiments show that this method has more advantages than other algorithms. More importantly, a combination of subjective privacy concerns and objective recommendation technology can reduce the influence of users' privacy concerns on their acceptance of mobile personalised service.

Research on collaborative filtering recommendation algorithm based on user interest for cloud computing

Aiming to resolve the mobile commerce scenario suggested problems, cloud computing technology and mobile user context are combined to propose a collaborative filtering model based on user interest in mobile scenarios. Through computing the scene similarity based on mobile users, we find similar scenarios constructed target user set current situation and then establish the item scoring scene and scoring matrix. Based on MapReduce, we propose a collaborative filtering recommendation method to realise parallel recommendation.

一种基于社会化信任的改进的协同过滤推荐模型和方法

一种基于社会化信任的改进的协同过滤推荐模型和方法

Research on collaborative filtering recommendation algorithm based on user interest for cloud computing

Aiming to resolve the mobile commerce scenario suggested problems, cloud computing technology and mobile user context are combined to propose a collaborative filtering model based on user interest in mobile scenarios. Through computing the scene similarity based on mobile users, we find similar scenarios constructed target user set current situation and then establish the item scoring scene and scoring matrix. Based on MapReduce, we propose a collaborative filtering recommendation method to realise parallel recommendation.

Collaborative filtering recommendation based on trust and emotion

With the development of personalized recommendations, information overload has been alleviated. However, the sparsity of the user-item rating matrix and the weak transitivity of trust still affect the recommendation accuracy in complex social network environments. Additionally, collaborative filtering based on users is vulnerable to shilling attacks due to neighbor preference recommendation. With the objective of overcoming these problems, a collaborative filtering recommendation method based on trust and emotion is proposed in this paper. First, we employ a method based on explicit and implicit satisfaction to alleviate the sparsity problems. Second, we establish trust relationships among users using objective and subjective trust. Objective trust is determined by similarity of opinion, including rating similarity and preference similarity. Subjective trust is determined by familiarity among users based on six degrees of separation. Third, based on the trust relationship, a set of trusted neighbors is obtained for a target user. Next, to further exclude malicious users or attackers from the neighbors, the set is screened according to emotional consistency among users, which is mined from implicit user behavior information. Finally, based on the ratings of items by the screened trusted neighbors and the trust relationships among the target user and these neighbors, we can obtain a list of recommendations for the target user. The experimental results show that the proposed method can improve the recommendation accuracy in the case of data sparsity, effectively resist shilling attacks, and achieve higher recommendation accuracy for cold start users compared to other methods.

A collaborative filtering recommendation method based on discrete quantum-inspired shuffled frog leaping algorithms in social networks

In social network recommendation systems, the rating score prediction accuracy of the collaborative filtering (CF) method depends on both the extraction of the nearest neighbors and the calculation of user/project similarity. Based on a similar principle to user/project behavior, this paper uses the maximum intersection method to extract the optimal neighbor candidate set, and presents a weighted adjusted cosine similarity method to compute user/project similarity. Furthermore, to optimize the weights of the method, a novel optimization method called the discrete quantum-inspired shuffled frog leaping (DQSFL) algorithm is proposed, which is based on the shuffled frog leaping algorithm and quantum information theory. The DQSFL algorithm uses quantum movement equations to search for the optimal location according to the co-evolution of the quantum frog colony. The experiments demonstrate that the CF recommendation method based on DQSFL can effectively solve the rating data sparseness problem in the similarity computation process to improve the accuracy of the rating score prediction, and provide a better recommended result than traditional CF algorithms.

Research on O2O take-away restaurant recommendation system: taking ele.me APP as an example

Online to Offline (O2O) take-away has the great potentialT for development in China, but with a large number of merchants taking part in O2O take-away APP, resulting in the problem of information overload. And the recommended system can effectively relieve the information overload of APP. In this paper, the O2O take-away restaurant recommendation system is studied in detail. By analyzing the current situation of the O2O takeaway restaurant recommendation system, we put forward a recommendation algorithm based on rank-centroid/analytic hierarchy process. Through transforming the recent booking preferences of user into the take-away service standard weight, we establish the model, combined with the case of ele.me APP, compute actual scores of the restaurants by the comprehensive score, and choose the high score of the restaurants to recommend. Compared with the mainstream collaborative filtering recommendation method, the proposed method is simple and computationally smaller.

A Tag-based Recommender System Framework for Social Bookmarking Websites

In social bookmarking websites, social tags contain rich information about individual preference in web resources. Nevertheless, the unsupervised way of tag creation makes the expressions of user's interests are troubled by tag semantic gap. Additionally, in social network sites, the user's interests are influenced by his/her friends' preferences. To handle the problem of personalised interest expression and to recommend the relevant web resource for the users, we propose a tag-based recommender system framework for social bookmarking websites, in which user, tag and resource profiles are expressed reciprocally in a unified form and the 'following interest' is defined based on social network analysis for computing the influence of social relationship on individual interests. We compare our method with several collaborative filtering-based recommendation methods using datasets collected from two social bookmarking websites. The results show that it improves the performance of resource recommendation and outperforms the baseline methods.

Integrated collaborative filtering recommendation in social cyber-physical systems

Cyber-physical systems are becoming part of our daily life, and a large number of data are generated at such an unprecedented rate that it becomes larger than ever before in social cyber-physical systems. As a consequence, it is highly desired to process these big data so that meaningful knowledge can be extracted from those vast and diverse data. Based on those large-scale data, using collaborative filtering recommendation methods to recommend some valuable clients or products for those e-commerce websites or users is considered as an effective way. In this work, we present an integrated collaborative filtering recommendation approach that combines item ratings, user ratings, and social trust for making better recommendations. In contrast to previous collaborative filtering recommendation works, integrated collaborative filtering recommendation approach takes full advantage of the correlation between data and takes into consideration the similarity between items, the similarity between users and two kind...

An explicit trust and distrust clustering based collaborative filtering recommendation approach

A SVD signs based trust and distrust clustering method is proposed.A trust inference method is proposed to compute indirect trust between users.A trust neighbors mining algorithm is proposed to discover trust users.A sparse rating complement algorithm is proposed to get dense user rating profiles.The TCCF method is efficient in terms of prediction accuracy and coverage. Clustering based recommender systems have been demonstrated to be efficient and scalable to large-scale datasets. However, due to the employment of dimensionality reduction techniques, clustering based recommendation approaches generally suffer from relatively low accuracy and coverage. To tackle these problems, some trust clustering based recommendation methods are proposed which cluster the social trust information other than the user-item ratings. Existing trust clustering based recommendation algorithms only consider trust relationships, regardless of the distrust information. In addition, these methods simply perform traditional collaborative filtering method in the detected trust communities, which cannot handle the data sparsity and cold start problems effectively. In order to solve these issues, in this paper, an explicit trust and distrust clustering based collaborative filtering recommendation method is proposed. Firstly, a SVD signs based clustering algorithm is proposed to process the trust and distrust relationship matrix in order to discover the trust communities. Secondly, a sparse rating complement algorithm is proposed to generate dense user rating profiles which alleviates the sparsity and cold start problems to a very large extent. Finally, the prediction of missing ratings can be obtained by combining the newly generated user rating profiles and the traditional collaborative filtering algorithm. Experimental results on real-world dataset demonstrate that our approach can effectively improve both the accuracy and coverage of recommendations as well as in the cold start situation.

A Book Recommendation Method Considered Readers and Literatures for University Literature Service

Because of the varieties of reader selection and literature categories, the rating matrix is often sparse and diffused excessively, that leads an inefficiency book recommendation. Aiming that, considered the implicit relation between reader group and literature classes, a collaborative cluster recommendation method has been constructed, the balance factor  is defined, which is used to coordinate the weight of reader group and literature classes. Finally, through the test and validity evaluation, the cluster method mentioned in the paper can get a more productive recommendation than traditional reader cluster method.

A collaborative filtering recommendation method based on TagIEA expert degree model

A collaborative filtering recommendation method based on TagIEA expert degree model

A collaborative filtering recommendation method based on TagIEA expert degree model

In recent years, social networking services and e-commerce have been developing rapidly. The research of recommending in e-commerce service mainly focused on using the collaborative filtering algorithm. But the algorithm had the limitations of data sparsity and cold start. This paper presents a model using TagIEA expert degree metrics in the context of social e-commerce services, where tag and expert degree information are integrated into the collaborative filtering algorithm. The comprehensive recommendation based on the TagIEA expert degree can effectively mitigate the problems of cold start and data sparsity. Finally, this paper verifies the effectiveness of the improved collaborative filtering algorithm by experiments.

A Recommendation Method basing on Synthetic Strategy for Agricultural Science and Technology Information

To ameliorate the limitations of traditional collaborative filtering technologies and enhance the recommendation quality of agricultural science and technology information, a collaborative filtering recommendation method based on synthetic strategy is proposed. Firstly, filter the user set and user-item rating matrix according to the location of target user, which can solve the regional problem. Then, predict ratings of items according to the similarity of users or item content, which can relax the impact of the sparse rating. In addition, add the rating time to the user-item rating matrix to distinguish the timeliness of the user preference, and add user preference shifting in the similarity formula as a factor which can express the similarity of users or item content better. Our method can not only guarantee the recommended information is local and suit to current season of agricultural production, but also ensure the recommending precision under sparse rating data.

Collaborative Filtering Recommendation on Users' Interest Sequences.

As an important factor for improving recommendations, time information has been introduced to model users’ dynamic preferences in many papers. However, the sequence of users’ behaviour is rarely studied in recommender systems. Due to the users’ unique behavior evolution patterns and personalized interest transitions among items, users’ similarity in sequential dimension should be introduced to further distinguish users’ preferences and interests. In this paper, we propose a new collaborative filtering recommendation method based on users’ interest sequences (IS) that rank users’ ratings or other online behaviors according to the timestamps when they occurred. This method extracts the semantics hidden in the interest sequences by the length of users’ longest common sub-IS (LCSIS) and the count of users’ total common sub-IS (ACSIS). Then, these semantics are utilized to obtain users’ IS-based similarities and, further, to refine the similarities acquired from traditional collaborative filtering approaches. With these updated similarities, transition characteristics and dynamic evolution patterns of users’ preferences are considered. Our new proposed method was compared with state-of-the-art time-aware collaborative filtering algorithms on datasets MovieLens, Flixster and Ciao. The experimental results validate that the proposed recommendation method is effective and outperforms several existing algorithms in the accuracy of rating prediction.