A hesitant fuzzy model of computational trust considering hesitancy,vagueness and uncertainty

The aim of this work is to introduce a trust model, which is highly consistent with the social nature of trust in computational domains. To this end, we propose a hesitant fuzzy multi-criteria decision making based computational trust model capable of taking into account the fundamental building blocks corresponding to the concept of trust. The proposed model is capable of considering the contextuality property of trust and the subjective priorities of the trustor regarding the chosen goal. This is due to viewing trust not as a single label or an integrated concept, but as a collection of trustworthiness facets that may form the trust decision in various contexts and toward different goals. The main benefit of the proposed model is the consideration of the hesitancy of recommenders and the trustor in the process of trust decision making which can create a more flexible mapping between the social and computational requirements of trust. This type of formulation also allows for taking into account the vagueness of the provided opinions. In addition to the vagueness of the provided opinions, the model is capable of considering the certainty of recommendations and its effect on the aggregation process of gathered opinions. In the proposed model, the taste of the recommenders and the similarity of opinions are also considered. This will allow the model to assign more weight to recommendations that have a similar taste compared to the trustor. Finally, taking into consideration the attitudes of the trustors toward change of personality that may occur for various entities in the environment is another advantage of the proposed model. A step-by-step illustrative example and the results of several experimental evaluations, which demonstrate the benefits of the proposed model, are also presented in this paper.     

A correlative denoising autoencoder to model social influence for top-N recommender system

In recent years,there are numerous works been proposed to leverage the techniques of deep learning to improve social-aware recommendation performance.In most cases,it requires a larger number of data to train a robust deep learning model,which contains a lot of parameters to fit training data.However,both data of user ratings and social networks are facing critical sparse problem,which makes it not easy to train a robust deep neural network model.Towards this problem,we propose a novel correlative denoising autoencoder(CoDAE)method by taking correlations between users with multiple roles into account to learn robust representations from sparse inputs of ratings and social networks for recommendation.We develop the CoDAE model by utilizing three separated autoencoders to learn user features with roles of rater,truster and trustee,respectively.Especially,on account of that each input unit of user vectors with roles of truster and trustee is corresponding to a particular user,we propose to utilize shared parameters to learn common information of the units that corresponding to same users.Moreover,we propose a related regularization term to learn correlations between user features that learnt by the three subnetworks of CoDAE model.We further conduct a series of experiments to evaluate the proposed method on two public datasets for Top-N recommendation task.The experimental results demonstrate that the proposed model outperforms state-of-the-art algorithms on rank-sensitive metrics of MAP and NDCG.     

Socialized healthcare service recommendation using deep learning

Socialized recommender system recommends reliable healthcare services for users. Ratings are predicted on the healthcare services by merging recommendations given by users who has social relations with the active users. However, existing works did not consider the influence of distrust between users. They recommend items only based on the trust relations between users. We therefore propose a novel deep learning-based socialized healthcare service recommender model, which recommends healthcare services with recommendations given by recommenders with both trust relations and distrust relations with the active users. The influences of recommenders, considering both the node information and the structure information, are merged via the deep learning model. Experimental results show that the proposed model outperforms the existing works on prediction accuracy and prediction coverage simultaneously, even for cold start users or users with very sparse trust relations. It is also computational less expensive.

     

Noisy but non-malicious user detection in social recommender systems

Social recommender systems largely rely on user-contributed data to infer users’ preference. While this feature has enabled many interesting applications in social networking services, it also introduces unreliability to recommenders as users are allowed to insert data freely. Although detecting malicious attacks from social spammers has been studied for years, little work was done for detecting Noisy but Non-Malicious Users (NNMUs), which refers to those genuine users who may provide some untruthful data due to their imperfect behaviors. Unlike colluded malicious attacks that can be detected by finding similarly-behaved user profiles, NNMUs are more difficult to identify since their profiles are neither similar nor correlated from one another. In this article, we study how to detect NNMUs in social recommender systems. Based on the assumption that the ratings provided by a same user on closely correlated items should have similar scores, we propose an effective method for NNMU detection by capturing and accumulating user’s “self-contradictions”, i.e., the cases that a user provides very different rating scores on closely correlated items. We show that self-contradiction capturing can be formulated as a constrained quadratic optimization problem w.r.t. a set of slack variables, which can be further used to quantify the underlying noise in each test user profile. We adopt three real-world data sets to empirically test the proposed method. The experimental results show that our method (i) is effective in real-world NNMU detection scenarios, (ii) can significantly outperform other noisy-user detection methods, and (iii) can improve recommendation performance for other users after removing detected NNMUs from the recommender system.     

A novel recommendation approach based on users’ weighted trust relations and the rating similarities

With the growing popularity of open social networks, approaches incorporating social relationships into recommender systems are gaining momentum, especially matrix factorization-based ones. The experiments in previous literatures indicate that social information is very effective in improving the performance of traditional recommendation algorithms. However, most of existing social recommendation methods only take one kind of social relations—trust information into consideration, which is far from satisfactory. Furthermore, most of the existing trust networks are binary, which results in the equal treatment to different users who are trusted by the same user in these methods. In this paper, based on matrix factorization methods, we propose a new approach to make recommendation with social information. Its novelty can be summarized as follows: (1) it shows how to add different weights on the social trust relationships among users based on the trustee’s competence and trustworthiness; (2) it incorporates the similarity relationships among users as a complement into the social trust relationships to enhance the computation of user’s neighborhood; (3) it can balance the influence of these two kinds of relationships based on user’s individuality adaptively. Experiments on Epinions and Ciao datasets demonstrate that our approach outperforms the state-of-the-art algorithms in terms of mean absolute error and root mean square error, in particular for the users who rated a few items.     

Guest Editors' Introduction: Recommender Systems

This special issue presents eight articles, five long and three short, on techniques to improve recommender systems. They cover improving such aspects as user interaction with recommenders, the quality of results presented to users, and user trust in presented recommendations. This article is part of a special issue on Recommender Systems.     

多Agent系统中基于认知的信任框架研究

基于认知角度提出了一种Agent间以预动(proactive)的方式建立信任的形式化框架.在框架中首先区分了代理与非代理情形下的信任并分别给出定义.从信任的定义出发,施信方(the trustor)针对信任建立基于认知的推理过程,并根据推理需要主动向受信方请求信息.在获得所需信息后,考虑到交互信息的可靠性问题,施信方在认知推理的基础上进行关于可靠性的模糊推理,并决定是否建立信任.通过这个框架,Agent间可以在缺乏直接交互经验或者第三方证言的情况下,以预动的方式动态地建立信任,并且在信任建立的过程中,可以纳入复杂的上下文约束.同时,通过认知推理与模糊推理的结合,可以根据场景的需要采用不同的规则,给信任的建立带来更大的灵活性.     

Enabling topic-level trust for collaborative information sharing

As a consequence of the exponential growth of Internet and its services, including social applications fostering collaboration on the Web, information sharing had become pervasive. This caused a crescent need of more powerful tools to help users with the task of selecting interesting resources. Recommender systems have emerged as a solution to evaluate the quality of massively user-generated contents in open environments and provide recommendations based not only on the user interests but also on the opinions of people with similar tastes. In addition to interest similarity, however, trustworthiness is a factor that recommenders have to consider in the selection of reliable peers for collaboration. Most approaches in this regard estimates trust base on global user profile similarity or history of exchanged opinions. In this paper, we propose a novel approach for agent-based recommendation in which trust is independently learned and evolved for each pair of interest topics two users have in common. Experimental results show that agents learning who to trust about certain topics reach better levels of precision than considering interest similarity exclusively.     

PerContRep: a practical reputation system for pervasive content services

Social network has extended its popularity from the Internet to mobile domain. Personal mobile devices can be self-organized and communicate with each other for instant social activities at any time and in any places to achieve pervasive social networking (PSN). In such a network, various content information flows. To which extent should mobile users trust it, whilst user privacy can also be preserved? Existing work has not yet seriously considered trust and reputation management, although trust plays an important role in PSN. In this paper, we propose PerContRep, a practical reputation system for pervasive content services that can assist trustworthy content selection and consumption in a pervasive manner. We develop a hybrid trust and reputation management model to evaluate node recommendation trust and content reputation in the context of frequent change of node pseudonyms. Simulations show the advantages of PerContRep in assisting user decisions and its effectiveness with regard to unfair rating attack, collaborative unfair rating attack, on-off attack and conflict behavior attack. A prototype system achieves positive user feedback on its usability and social acceptance.     

Aligning principal and agent’s incentives: A principal–agent perspective of social networking sites

The viability of networked communities depends on the creation and disclosure of user-generated content and the frequency of user visitation (Facebook 10-K Annual Report, 2012). However, little is known about how to align the interests of user and social networking sites. In this study, we draw upon the principal-agent perspective to extend Pavlou et al.’s uncertainty mitigation model of online exchange relationships (2007) and propose an empirically tested model for aligning the incentives of the principal (user) and the agent (service provider). As suggested by Pavlou et al., we incorporated a multi-dimensional measure of trust: trust of provider and trust of members. The proposed model is empirically tested with survey data from 305 adults aged 20-55. The results support our model, delineating how real individuals with bounded rationality actually make decision about information disclosure under uncertainty in the social networking site context. There is show little to no relationship between online privacy concerns and information disclosure on online social network sites. Perceived benefits provide the linkage between the incentives of principal (user) and agent (provider) while usage intensity demonstrated the most significant impact on information disclosure. We argue that the phenomenon may be explained through Communication Privacy Management Theory. The present study enhances our understanding of agency theory and human judgment theory in the context of social media. Practical implications for understanding and facilitating online social exchange relationships are also discussed.     

垂直学习社区基于学习兴趣与风格的社会化推荐算法

垂直学习社区包含了海量的学习资源,出现了信息过载现象,个性化推荐是解决这个难题的方法之一.但垂直学习社区中评分数据稀疏而文本、社交信息丰富,传统的协同过滤推荐算法不完全适用.基于用户产生的文本和行为信息,利用作者主题模型构建新的用户学习兴趣相似度衡量模型;根据用户交互行为信息综合考虑信任与不信任因素构建用户全面信任关系计算全面信任度;通过分析用户多维度学习行为模式,自动识别用户学习风格;最后提出融合兴趣相似度、全面信任度及学习风格的社会化推荐算法.用垂直学习社区网站CSDN实际数据集进行了实验分析.结果表明本文提出的推荐方法能更好向用户推荐其感兴趣的学习资源,有效地提高了推荐精度,进而提高用户学习效果.     

Trust-aware recommendation based on heterogeneous multi-relational graphs fusion

Users’ trust relations have a significant influence on their choice towards different products. However, few recommendation or prediction algorithms both consider users’ social trust relations and item-related knowledge, which makes them difficult to cope with cold start and the data sparsity problems. In this paper, we propose a novel trust-ware recommendation method based on heterogeneous multi-relational graphs fusion, termed as T-MRGF. In contrast with other traditional methods, it fuses the user-related and item-related graphs with the user–item interaction graph and fully utilizes the high-level connections existing in heterogeneous graphs. Specifically, we first establish the user–user trust relation graph, user–item interaction graph and item–item knowledge graph, and the user feature and item feature, which have been obtained from the user–item graph, are used as the input of the user-related graph and the item-related graph respectively. The fusion is achieved through the cascade of feature vectors before and after feature propagation. In this way, the heterogeneous multi-relational graphs are fused for the feature propagation, which largely refines the user and item representation for model prediction. Simulation results show that the proposed method significantly improve the recommendation performance compared to the state-of-the-art KG-based algorithms both in accuracy and training efficiency.     

A comparative study of three social networking websites

Recently, the number of social networking sites is rapidly increasing, and the number of users joining these sites is dramatically increasing as well. This paper aims at comprehensively comparing three social networking sites, and provides an in-depth analysis. We compare three of the most popular social networking sites, i.e., Facebook, Twitter and MySpace. Specifically, we evaluate those social networking sites based on four criteria (i.e., navigation, interactivity, source credibility and intelligence). For each criterion, we propose a list of measures for the comparison. The comparison essentially explores the differences and commonalities among those social networking sites. Based on the analysis of the comparison, a user study is conducted to evaluate the three websites.     

社交网络用户影响力分析ABP算法研究与应用

社交网络作为一种交往方式,已经深入人心。其用户数据在这个大数据时代蕴藏着大量的价值。随着Twitter API的开放,社交网络Twitter俨然成为一个深受欢迎的研究对象,而用户影响力更是其中的研究热点。PageRank算法计算用户影响力已经由来已久,但是它太依赖于用户之间的关注关系,排名不具备时效性。引入用户活跃度的改进PageRank算法,具备一定的时效性,但是不具有足够的说服力和准确性。研究了一种新的基于时间分布用户活跃度的ABP算法,并为不同时段的活跃度加以相应的时效权重因子。最后,以Twitter为研究对象,结合社交关系网,通过实例分析说明ABP算法更具时效性和说服力,可以比较准确地提高活跃用户的排名,降低非活跃用户排名。     

A group trust metric for identifying people of trust in online social networks

With the growth of social network services, the need for identifying trustworthy people has become a primary concern in order to protect users’ vast amounts of information from being misused by unreliable users. In this study, we propose the extended Advogato trust metric that facilitates the identification of trustworthy users associated with each individual user. By incorporating the strength of social relationships, we recursively diffuse a capacity of a target user throughout his/her personal network. Based on the capacity propagation, this paper also presents the capacity-first maximum flow method capable of finding the strongest path pertinent to discovering an ordered set of reliable users and preventing unreliable users from accessing personal networks. Experimental results demonstrate that our approach has advantages over existing representative methods in terms of both the discovery of reliable users and the preventability of unreliable users.     

Brand interactions and social media: Enhancing user loyalty through social networking sites

This paper aims to investigate how user loyalty can be achieved and maintained through social networking sites. More specifically, we intend to test the relationships between brands, user loyalty and social media. The research thus provides insights into user-brand relationships through social media and argues how loyal customers can be through social networking websites. Although there are considerable numbers of studies about loyalty; there exists very limited work studying user loyalty through social networking websites. This research presents clearly the reasons for engaging with brands online and examines user behaviors and loyalty. Research provided strong evidence that majority of the social network users follow brand fan pages via social media, even though they have different reasons to do so. The study also measures users’ behavioral and attitudinal loyalty behaviors. Their level of trust to the information they obtained about brands through social media is also established. The hypotheses tested show that brands and customer satisfaction are both positively related to users’ behavioral loyalty.     

Experiments of Trust Prediction in Social Networks by Artificial Neural Networks

Social network online services are growing at an exponential pace, both in quantity of users and diversity of services; thus, the evaluation of trust in the interaction among users and toward the system is a central issue from the user point of view. Trust can be grounded in past direct experience or in the indirect information provided by trusted third-party users shaping the trustee reputation. When there is no previous history of interactions, the truster must resort to some form of prediction in order to establish Trust or Distrust on a potential trustee. In this study, we deal with the prediction of trust relationships on the basis of reputation information. Trust can be positive or negative (Distrust), hence, we have a two-class problem. Feature vectors for the classification have binary-valued components. Artificial neural network and statistical classifiers provide state-of-the-art results with these features on a benchmarking trust database. In this article, we propose the application of a sample generation method for the minority class in order to reduce some of the effect of class imbalance among Trust and Distrust classes. Specifically, the approach shows high resiliency to system growth.     

Benevolence trust: a key determinant of user continuance use of online social networks

Online social networking (OSN) has attracted increased attention and growing membership in recent years. In this paper, we propose and test an extended and unified theory of acceptance and use of technology (UTAUT) model, including the additional areas of satisfaction, credibility trust, and benevolence trust, using an empirical survey of 676 OSN users to examine the influence of these factors. The results of regression analysis showed that the four key constructs of UTAUT (social influence, performance expectancy, effort expectancy, and facilitating conditions), as well as satisfaction, credibility trust, and benevolence trust, are all direct determinants of user continuance use of OSN. By comparing the coefficients of regression analysis, the relative importance of each determinant was also demonstrated. Results further indicate that benevolence trust has a much more significant effect on user continuance use of OSN than any other factor. A discussion is offered on the implications of these findings for OSN managers with regard to marketing and operations.     

Adaptive website recommendations with AWESOME

Recommendations are crucial for the success of large websites. While there are many ways to determine recommendations, the relative quality of these recommenders depends on many factors and is largely unknown. We present the architecture and implementation of AWESOME (Adaptive website recommendations), a data warehouse-based recommendation system. It allows the coordinated use of a large number of recommenders to automatically generate website recommendations. Recommendations are dynamically selected by efficient rule-based approaches utilizing continuously measured user feedback on presented recommendations. AWESOME supports a completely automatic generation and optimization of selection rules to minimize website administration overhead and quickly adapt to changing situations. We propose a classification of recommenders and use AWESOME to comparatively evaluate the relative quality of several recommenders for a sample website. Furthermore, we propose and evaluate several rule-based schemes for dynamically selecting the most promising recommendations. In particular, we investigate two-step selection approaches that first determine the most promising recommenders and then apply their recommendations for the current situation. We also evaluate one-step schemes that try to directly determine the most promising recommendations.