Conceptual Framework for Recommendation System Based on Distributed User Ratings
07 Dec 2003-pp 115-122
TL;DR: The distributed recommender system with FOAF on P2P environment can recommend users without the centralized server, which keeps updating their profiles and RFR (Recommend-Feedback-Re-recommend) algorithm is suggested to improve the confidence of recommendation.
Abstract: A recommender system is an automated collaborative filtering system that helps users to decide what they are interested in by extracting their own preferences. Most studies related to recommendation system have focused on centralized environment causing several serious problems such as fraud rating and privacy issues. In this paper, however, we propose the distributed recommender system with FOAF on P2P environment. This system can recommend users without the centralized server, which keeps updating their profiles. In order to find out the most eligible users to be recommended, user grouping (selecting objects) is one of the most important processes in the whole recommendation. Thereby, we have exploited cosine-based similarity method to cluster the users in the same level. More importantly, RFR (Recommend-Feedback-Re-recommend) algorithm is suggested to improve the confidence of recommendation. For the experiment, we have used the MovieLens datasets and have tested the performance by using “F1-measure” and Mean Absolute Error (MAE). As a conclusion, we have improved the robustness of the system. Also, we have shown the possibility of distributed recommender system on semantic web.
Citations
More filters
TL;DR: A robust information diffusion model is proposed to detect the malicious peers from which the risks was originated on P2P networks and trace social interactions among peers to identify a recommendation flow and collect them.
Abstract: Knowledge management systems have been inter-networked with each other on distributed environment, e.g., peer-to-peer (P2P) networks. However, as some of users take malicious actions, the corresponding information (or knowledge) on the P2P networks might be contaminated and distorted. In this paper, we propose a robust information diffusion (or propagation) model to detect the malicious peers from which the risks (e.g., information distortion) was originated on P2P networks. Thereby, we want to trace social interactions among peers to identify a recommendation flow and collect them. Given a set of recommendation flows, statistical sequence mining method is exploited to discover a certain social position which provides peculiar patterns on the P2P networks. For evaluating the proposed method, we conducted two experimentations with NetLogo simulation platform for risk discovery on social network.
28 citations
Journal Article•
TL;DR: A novel method for visual explanation of the recommender system on social network by using the MovieLens dataset on a social network constructed with FOAF to simulate the recommendation flow.
Abstract: In contrast with centralized recommender systems, social recommendation algorithm is applied to the item rating data on social networks. Meaningful recom- mendation can be uncovered by the topology of social network as well as the similarity between users. More importantly, this information becomes propagated into the users in the estimated same groups. As the goal of this paper, we propose a novel method for visual explanation of the recommender system on social network. For experiments, we simulate the recommendation flow by using the MovieLens dataset on a social network constructed with FOAF.
20 citations
24 Oct 2011
TL;DR: The demo of P2Prec's main services are described using the prototype implemented as an application of SON, an open source development platform for P2P networks using web services, JXTA and OSGi.
Abstract: P2Prec is a social-based P2P recommendation system for large-scale content sharing that leverages content-based and social-based recommendation. The main idea is to recommend high quality documents related to query topics and contents held by useful friends (of friends) of the users, by exploiting friendship networks. We have implemented a prototype of P2Prec using the Shared-Data Overlay Network (SON), an open source development platform for P2P networks using web services, JXTA and OSGi. In this paper, we describe the demo of P2Prec's main services (installing P2Prec peers, initializing peers, gossiping topics of interest among friends, key-word querying for contents) using our prototype implemented as an application of SON.
17 citations
Cites background from "Conceptual Framework for Recommenda..."
...These systems exploit the preferences and relations of users’ friends (of friends) [2] or the trust relations [8] between users to aggregate the neighbors of each user....
[...]
05 Sep 2006
TL;DR: A novel approach is presented to provide the enhanced prediction quality supporting the protection against the influence of malicious ratings, or unreliable users, and an item-based approach is employed to overcome the sparsity and scalability problems.
Abstract: As the Internet infrastructure has been developed, a substantial number of diverse effective applications have attempted to achieve the full potential offered by the infrastructure. Collaborative Filtering recommender system, one of the most representative systems for personalized recommendations in E-commerce on the Web, is a system assisting users in easily finding the useful information. But traditional collaborative filtering suffers some weaknesses with quality evaluation: the sparsity of the data, scalability, unreliable users. To address these issues, we have presented a novel approach to provide the enhanced prediction quality supporting the protection against the influence of malicious ratings, or unreliable users. In addition, an item-based approach is employed to overcome the sparsity and scalability problems. The proposed method combines the item confidence and item similarity, collectively called item trust using this value for online predictions. The experimental evaluation on MovieLens datasets shows that the proposed method brings significant advantages both in terms of improving the prediction quality and in dealing with malicious datasets.
15 citations
Cites background from "Conceptual Framework for Recommenda..."
...And a number of researches have been proposed and challenged to address these problems related to collaborative filtering [2, 5, 6, 7, 10, 13]....
[...]
...An ongoing area of current is a distributed recommender system [10, 12]....
[...]
...In addition, distributed recommender systems have been proposed to deal with the existing weaknesses [7, 10, 12]....
[...]
TL;DR: A trust-based recommendation service for a mobile tourist guide that uses the notion of directly and indirectly trusted peers that combines information about the peers' ratings on sights, interpersonal trust and geographical constraints is presented.
Abstract: Recommender systems in a travel guide suggest touristic sites a user may like. Typically, people are more willing to trust recommendations from people they know. We present a trust-based recommendation service for a mobile tourist guide that uses the notion of directly and indirectly trusted peers. The recommendations combine information about the peers' ratings on sights, interpersonal trust and geographical constraints. We created two trust propagation models to spread trust information throughout the traveller peer group. Our prototype supports six trust-based, location-aware recommendation algorithms.
15 citations
Cites background from "Conceptual Framework for Recommenda..."
...The Recommend-Feedback-Re-recommend (RFR) conceptual framework [8] learns the users’ preference from an FOAF-based environment....
[...]
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
"Conceptual Framework for Recommenda..." refers methods in this paper
...This system is also called ratings-based automated recommender system, because filtering is executed by the explicit opinions of people from a close-knit community [8]....
[...]
22 Oct 1994
TL;DR: GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles, and protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction.
Abstract: Collaborative filters help people make choices based on the opinions of other people. GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles. News reader clients display predicted scores and make it easy for users to rate articles after they read them. Rating servers, called Better Bit Bureaus, gather and disseminate the ratings. The rating servers predict scores based on the heuristic that people who agreed in the past will probably agree again. Users can protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction. The entire architecture is open: alternative software for news clients and Better Bit Bureaus can be developed independently and can interoperate with the components we have developed.
5,644 citations
"Conceptual Framework for Recommenda..." refers methods in this paper
...The GroupLens system that developed by research group in University of Minnesota is based on rating for collaborative filtering of netnews in order to help people find relevant articles in the huge stream of available articles [7]....
[...]
PARC1
TL;DR: Tapestry is intended to handle any incoming stream of electronic documents and serves both as a mail filter and repository; its components are the indexer, document store, annotation store, filterer, little box, remailer, appraiser and reader/browser.
Abstract: The Tapestry experimental mail system developed at the Xerox Palo Alto Research Center is predicated on the belief that information filtering can be more effective when humans are involved in the filtering process. Tapestry was designed to support both content-based filtering and collaborative filtering, which entails people collaborating to help each other perform filtering by recording their reactions to documents they read. The reactions are called annotations; they can be accessed by other people’s filters. Tapestry is intended to handle any incoming stream of electronic documents and serves both as a mail filter and repository; its components are the indexer, document store, annotation store, filterer, little box, remailer, appraiser and reader/browser. Tapestry’s client/server architecture, its various components, and the Tapestry query language are described.
4,299 citations
"Conceptual Framework for Recommenda..." refers background in this paper
...Tapestry is one of the earliest systems of collaborative filteringbased recommender system [6]....
[...]
[...]
TL;DR: This special section includes descriptions of five recommender systems, which provide recommendations as inputs, which the system then aggregates and directs to appropriate recipients, and which combine evaluations with content analysis.
Abstract: Recommender systems assist and augment this natural social process. In a typical recommender system people provide recommendations as inputs, which the system then aggregates and directs to appropriate recipients. In some cases the primary transformation is in the aggregation; in others the system’s value lies in its ability to make good matches between the recommenders and those seeking recommendations. The developers of the first recommender system, Tapestry [1], coined the phrase “collaborative filtering” and several others have adopted it. We prefer the more general term “recommender system” for two reasons. First, recommenders may not explictly collaborate with recipients, who may be unknown to each other. Second, recommendations may suggest particularly interesting items, in addition to indicating those that should be filtered out. This special section includes descriptions of five recommender systems. A sixth article analyzes incentives for provision of recommendations. Figure 1 places the systems in a technical design space defined by five dimensions. First, the contents of an evaluation can be anything from a single bit (recommended or not) to unstructured textual annotations. Second, recommendations may be entered explicitly, but several systems gather implicit evaluations: GroupLens monitors users’ reading times; PHOAKS mines Usenet articles for mentions of URLs; and Siteseer mines personal bookmark lists. Third, recommendations may be anonymous, tagged with the source’s identity, or tagged with a pseudonym. The fourth dimension, and one of the richest areas for exploration, is how to aggregate evaluations. GroupLens, PHOAKS, and Siteseer employ variants on weighted voting. Fab takes that one step further to combine evaluations with content analysis. ReferralWeb combines suggested links between people to form longer referral chains. Finally, the (perhaps aggregated) evaluations may be used in several ways: negative recommendations may be filtered out, the items may be sorted according to numeric evaluations, or evaluations may accompany items in a display. Figures 2 and 3 identify dimensions of the domain space: The kinds of items being recommended and the people among whom evaluations are shared. Consider, first, the domain of items. The sheer volume is an important variable: Detailed textual reviews of restaurants or movies may be practical, but applying the same approach to thousands of daily Netnews messages would not. Ephemeral media such as netnews (most news servers throw away articles after one or two weeks) place a premium on gathering and distributing evaluations quickly, while evaluations for 19th century books can be gathered at a more leisurely pace. The last dimension describes the cost structure of choices people make about the items. Is it very costly to miss IT IS OFTEN NECESSARY TO MAKE CHOICES WITHOUT SUFFICIENT personal experience of the alternatives. In everyday life, we rely on
3,993 citations
"Conceptual Framework for Recommenda..." refers methods in this paper
...To solve these problems and to increase the performance of the recommender system such as robustness, MAE and “F1-measure”, researchers have suggested a number of alternative approaches using various techniques [3], [4]....
[...]
17 Oct 2000
TL;DR: This paper investigates several te hniques for analyzing large-s ale pur hase and preferen e data for the purpose of producing useful re ommendations to ustomers and devise and apply their ombinations on the authors' data sets to ompare for re Ommendation quality and performan e.
Abstract: Re ommender systems apply statisti al and knowledge disovery te hniques to the problem of making produ t re ommendations during a live ustomer intera tion and they are a hieving widespread su ess in E-Commer e nowadays. In this paper, we investigate several te hniques for analyzing large-s ale pur hase and preferen e data for the purpose of produ ing useful re ommendations to ustomers. In parti ular, we apply a olle tion of algorithms su h as traditional data mining, nearest-neighbor ollaborative ltering, and dimensionality redu tion on two di erent data sets. The rst data set was derived from the web-pur hasing transa tion of a large Eommer e ompany whereas the se ond data set was olle ted from MovieLens movie re ommendation site. For the experimental purpose, we divide the re ommendation generation pro ess into three sub pro esses{ representation of input data, neighborhood formation, and re ommendation generation. We devise di erent te hniques for di erent sub pro esses and apply their ombinations on our data sets to ompare for re ommendation quality and performan e.
1,913 citations
"Conceptual Framework for Recommenda..." refers background or methods in this paper
...For the experiment, we selected 450 users to use only about 66,926 rating dataset [9]....
[...]
...They also offer an experimental data source and a framework for studying user interface issues related to recommender systems [9]....
[...]