Improving Prediction Accuracy in Trust-Aware Recommender Systems
05 Jan 2010-pp 1-9
TL;DR: This paper proposes an approach for improving accuracy of predictions in trust-aware recommender systems and shows that the proposed approach of reconstructing the trust network gives substantially better prediction accuracy than the original approach of using all trust statements in the network.
Abstract: Trust-aware recommender systems are intelligent technology applications that make use of trust information and user personal data in social networks to provide personalized recommendations. Earlier research in trust-aware systems have shown that the ability of trust-based systems to make accurate predictions coupled with their robustness from shilling attacks make them a better alternative than traditional recommender systems. In this paper we propose an approach for improving accuracy of predictions in trust-aware recommender systems. In our approach, we first reconstruct the trust network. Trust network is reconstructed by removing trust links between users having correlation coefficient below a specified threshold value. For prediction calculation we compare three different approaches based on trust and correlation. We show through experiments on real life Epinions data set that our proposed approach of reconstructing the trust network gives substantially better prediction accuracy than the original approach of using all trust statements in the network.
Citations
More filters
TL;DR: Various attack types are described and new dimensions for attack classification are introduced and detailed description of the proposed detection and robust recommendation algorithms are given.
Abstract: Online vendors employ collaborative filtering algorithms to provide recommendations to their customers so that they can increase their sales and profits. Although recommendation schemes are successful in e-commerce sites, they are vulnerable to shilling or profile injection attacks. On one hand, online shopping sites utilize collaborative filtering schemes to enhance their competitive edge over other companies. On the other hand, malicious users and/or competing vendors might decide to insert fake profiles into the user-item matrices in such a way so that they can affect the predicted ratings on behalf of their advantages. In the past decade, various studies have been conducted to scrutinize different shilling attacks strategies, profile injection attack types, shilling attack detection schemes, robust algorithms proposed to overcome such attacks, and evaluate them with respect to accuracy, cost/benefit, and overall performance. Due to their popularity and importance, we survey about shilling attacks in collaborative filtering algorithms. Giving an overall picture about various shilling attack types by introducing new classification attributes is imperative for further research. Explaining shilling attack detection schemes in detail and robust algorithms proposed so far might open a lead to develop new detection schemes and enhance such robust algorithms further, even propose new ones. Thus, we describe various attack types and introduce new dimensions for attack classification. Detailed description of the proposed detection and robust recommendation algorithms are given. Moreover, we briefly explain evaluation of the proposed schemes. We conclude the paper by discussing various open questions.
273 citations
Cites background from "Improving Prediction Accuracy in Tr..."
...In order to enhance robustness, Zhang and Xu (2007) recommend utilizing topic-level trust-based prediction algorithm....
[...]
...Trust-aware recommender systems are more robust prediction schemes than traditional ones against shilling attacks (Massa and Avesani 2007; Ray and Mahanti 2010)....
[...]
TL;DR: Results demonstrate that this novel method to incorporate social trust information (i.e., trusted neighbors explicitly specified by users) in providing recommendations outperforms other counterparts both in terms of accuracy and coverage.
Abstract: Providing high quality recommendations is important for e-commerce systems to assist users in making effective selection decisions from a plethora of choices. Collaborative filtering is a widely accepted technique to generate recommendations based on the ratings of like-minded users. However, it suffers from several inherent issues such as data sparsity and cold start. To address these problems, we propose a novel method called ''Merge'' to incorporate social trust information (i.e., trusted neighbors explicitly specified by users) in providing recommendations. Specifically, ratings of a user's trusted neighbors are merged to complement and represent the preferences of the user and to find other users with similar preferences (i.e., similar users). In addition, the quality of merged ratings is measured by the confidence considering the number of ratings and the ratio of conflicts between positive and negative opinions. Further, the rating confidence is incorporated into the computation of user similarity. The prediction for a given item is generated by aggregating the ratings of similar users. Experimental results based on three real-world data sets demonstrate that our method outperforms other counterparts both in terms of accuracy and coverage.
233 citations
Cites background or methods from "Improving Prediction Accuracy in Tr..."
...In addition, as indicated by [27] and as a general belief, even trusted users may not share similar preference and so does the social similarity....
[...]
...In addition, most previous works are only evaluated on a single data set [4,8,25,27]....
[...]
...Nevertheless, we adopt the weighted average because the two most related works [25,27] also take the same equation....
[...]
...Another recent work using the explicit trust network is proposed by [27]....
[...]
...RN denotes the approach proposed by [27] that predicts item ratings by reconstructing the trust networks....
[...]
TL;DR: Existing trust models from a game theoretic perspective are analyzed to highlight the special implications of including human beings in an MAS, and a possible research agenda to advance the state of the art in this field is proposed.
Abstract: In open and dynamic multiagent systems (MASs), agents often need to rely on resources or services provided by other agents to accomplish their goals. During this process, agents are exposed to the risk of being exploited by others. These risks, if not mitigated, can cause serious breakdowns in the operation of MASs and threaten their long-term wellbeing. To protect agents from the uncertainty in the behavior of their interaction partners, the age-old mechanism of trust between human beings is re-contexted into MASs. The basic idea is to let agents self-police the MAS by rating each other on the basis of their observed behavior and basing future interaction decisions on such information. Over the past decade, a large number of trust management models were proposed. However, there is a lack of research effort in several key areas, which are critical to the success of trust management in MASs where human beings and agents coexist. The purpose of this paper is to give an overview of existing research in trust management in MASs. We analyze existing trust models from a game theoretic perspective to highlight the special implications of including human beings in an MAS, and propose a possible research agenda to advance the state of the art in this field.
205 citations
Cites methods from "Improving Prediction Accuracy in Tr..."
...For example, the Epinions dataset and the Extended Epinions dataset compiled by [92] have been used to analyze the performance of trust models concerned with bootstrapping and collaborative recommendation [46], [93]–[95]; in [33], data from the FilmTrust social network are used to analyze the performance of the proposed SUNNY socio-cognitive trust model; rating information from eBay is used in [38]; the web spam dataset from Yahoo! is used in [49] to evaluate their model for propagating trust and distrust in the web; and data...
[...]
16 Jul 2012
TL;DR: Ratings of a user's trusted neighbors are merged to represent the preference of the user and to find similar other users for generating recommendations, demonstrating that this method is more effective than other approaches, both in accuracy and coverage of recommendations.
Abstract: Providing high quality recommendations is important for online systems to assist users who face a vast number of choices in making effective selection decisions. Collaborative filtering is a widely accepted technique to provide recommendations based on ratings of similar users. But it suffers from several issues like data sparsity and cold start. To address these issues, in this paper, we propose a simple but effective method, namely "Merge", to incorporate social trust information (i.e. trusted neighbors explicitly specified by users) in providing recommendations. More specifically, ratings of a user's trusted neighbors are merged to represent the preference of the user and to find similar other users for generating recommendations. Experimental results based on three real data sets demonstrate that our method is more effective than other approaches, both in accuracy and coverage of recommendations.
99 citations
TL;DR: This paper briefly discusses the related survey papers about shilling attacks in CFRSs, explains profile injection attack strategies, shilling attack detection schemes and robust recommendation algorithms proposed so far in detail, and briefly explains evaluation metrics of the proposed schemes.
Abstract: Collaborative filtering recommender systems (CFRSs) have already been proved effective to cope with the information overload problem since they merged in the past two decades. However, CFRSs are highly vulnerable to shilling or profile injection attacks since their openness. Ratings injected by malicious users seriously affect the authenticity of the recommendations as well as users’ trustiness in the recommendation systems. In the past two decades, various studies have been conducted to scrutinize different profile injection attack strategies, shilling attack detection schemes, robust recommendation algorithms, and to evaluate them with respect to accuracy and robustness. Due to their popularity and importance, we survey about shilling attacks in CFRSs. We first briefly discuss the related survey papers about shilling attacks and analyze their deficiencies to illustrate the necessity of this paper. Next we give an overall picture about various shilling attack types and their deployment modes. Then we explain profile injection attack strategies, shilling attack detection schemes and robust recommendation algorithms proposed so far in detail. Moreover, we briefly explain evaluation metrics of the proposed schemes. Last, we discuss some research directions to improve shilling attack detection rates robustness of collaborative recommendation, and conclude this paper.
78 citations
Cites background from "Improving Prediction Accuracy in Tr..."
...Trust-aware recommender systems are more robust prediction schemes than traditional ones against shilling attacks (Lacoste-Julien et al. 2013; Ray and Mahanti 2010)....
[...]
References
More filters
01 Apr 2001
TL;DR: This paper analyzes item-based collaborative ltering techniques and suggests that item- based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.
Abstract: Recommender systems apply knowledge discovery techniques to the problem of making personalized recommendations for information, products or services during a live interaction. These systems, especially the k-nearest neighbor collaborative ltering based ones, are achieving widespread success on the Web. The tremendous growth in the amount of available information and the number of visitors to Web sites in recent years poses some key challenges for recommender systems. These are: producing high quality recommendations, performing many recommendations per second for millions of users and items and achieving high coverage in the face of data sparsity. In traditional collaborative ltering systems the amount of work increases with the number of participants in the system. New recommender system technologies are needed that can quickly produce high quality recommendations, even for very large-scale problems. To address these issues we have explored item-based collaborative ltering techniques. Item-based techniques rst analyze the user-item matrix to identify relationships between di erent items, and then use these relationships to indirectly compute recommendations for users. In this paper we analyze di erent item-based recommendation generation algorithms. We look into di erent techniques for computing item-item similarities (e.g., item-item correlation vs. cosine similarities between item vectors) and di erent techniques for obtaining recommendations from them (e.g., weighted sum vs. regression model). Finally, we experimentally evaluate our results and compare them to the basic k-nearest neighbor approach. Our experiments suggest that item-based algorithms provide dramatically better performance than user-based algorithms, while at the same time providing better quality than the best available userbased algorithms.
8,634 citations
"Improving Prediction Accuracy in Tr..." refers background in this paper
...There are two primary approaches which are used to build collaborative filtering (CF) memory based recommender systems, user-based CF [5] and item-based CF [12]....
[...]
04 Jan 2000
TL;DR: In this article, a trust model that is grounded in real-world social trust characteristics, and based on a reputation mechanism, or word-of-mouth, is proposed for the virtual medium.
Abstract: At any given time, the stability of a community depends on the right balance of trust and distrust. Furthermore, we face information overload, increased uncertainty and risk taking as a prominent feature of modern living. As members of society, we cope with these complexities and uncertainties by relying trust, which is the basis of all social interactions. Although a small number of trust models have been proposed for the virtual medium, we find that they are largely impractical and artificial. In this paper we provide and discuss a trust model that is grounded in real-world social trust characteristics, and based on a reputation mechanism, or word-of-mouth. Our proposed model allows agents to decide which other agents' opinions they trust more and allows agents to progressively tune their understanding of another agent's subjective recommendations.
1,487 citations
19 Oct 2007
TL;DR: This work proposes to replace the step of finding similar users with the use of a trust metric, an algorithm able to propagate trust over the trust network and to estimate a trust weight that can be used in place of the similarity weight.
Abstract: Recommender Systems based on Collaborative Filtering suggest to users items they might like. However due to data sparsity of the input ratings matrix, the step of finding similar users often fails. We propose to replace this step with the use of a trust metric, an algorithm able to propagate trust over the trust network and to estimate a trust weight that can be used in place of the similarity weight. An empirical evaluation on Epinions.com dataset shows that Recommender Systems that make use of trust information are the most effective in term of accuracy while preserving a good coverage. This is especially evident on users who provided few ratings.
1,137 citations
"Improving Prediction Accuracy in Tr..." refers background in this paper
...Recent research on trust aware recommender systems [4, 6, 7, 8] has shown that they are more robust against shilling attacks and are more capable of generating recommendations for new users in the system....
[...]
...Initial research [11] on trust-aware recommender systems used trust values derived from ratings, subsequent research on trust-ware recommender systems [4,6,7] used explicitly made trust statements....
[...]
10 Jan 2005
TL;DR: This paper proposes that the trustworthiness of users must be an important consideration in guiding recommendation and presents two computational models of trust and shows how they can be readily incorporated into standard collaborative filtering frameworks in a variety of ways.
Abstract: Recommender systems have proven to be an important response to the information overload problem, by providing users with more proactive and personalized information services. And collaborative filtering techniques have proven to be an vital component of many such recommender systems as they facilitate the generation of high-quality recom-mendations by leveraging the preferences of communities of similar users. In this paper we suggest that the traditional emphasis on user similarity may be overstated. We argue that additional factors have an important role to play in guiding recommendation. Specifically we propose that the trustworthiness of users must be an important consideration. We present two computational models of trust and show how they can be readily incorporated into standard collaborative filtering frameworks in a variety of ways. We also show how these trust models can lead to improved predictive accuracy during recommendation.
897 citations
Additional excerpts
...Initial research [11] on trust-aware recommender systems used trust values derived from ratings, subsequent research on trust-ware recommender systems [4,6,7] used explicitly made trust statements....
[...]
25 Oct 2004
TL;DR: An empirical evaluation on Epinions.com dataset shows that trust propagation can increase the coverage of Recommender Systems while preserving the quality of predictions.
Abstract: Recommender Systems allow people to find the resources they need by making use of the experiences and opinions of their nearest neighbours. Costly annotations by experts are replaced by a distributed process where the users take the initiative. While the collaborative approach enables the collection of a vast amount of data, a new issue arises: the quality assessment. The elicitation of trust values among users, termed “web of trust”, allows a twofold enhancement of Recommender Systems. Firstly, the filtering process can be informed by the reputation of users which can be computed by propagating trust. Secondly, the trust metrics can help to solve a problem associated with the usual method of similarity assessment, its reduced computability. An empirical evaluation on Epinions.com dataset shows that trust propagation can increase the coverage of Recommender Systems while preserving the quality of predictions. The greatest improvements are achieved for users who provided few ratings.
636 citations
"Improving Prediction Accuracy in Tr..." refers background or methods in this paper
...A detailed analysis of the data set can be found at [6, 8]....
[...]
...As trust statement values in the dataset were all 1, we use a linear decay approach for propagating trust [6]....
[...]
...Similarly in [6] superiority of trust-based systems has been experimentally shown on data from Epinions....
[...]
...Recent research on trust aware recommender systems [4, 6, 7, 8] has shown that they are more robust against shilling attacks and are more capable of generating recommendations for new users in the system....
[...]
...Trust statements are weighted, subjective, context dependent and asymmetric[6]....
[...]