Integrating Multi-Criteria Collaborative Filtering and Trust filtering for personalized Recommender Systems
Published 1 April 2011
Qusai Y. Shambour, Jie Lü
Citations16
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Empirical results demonstrate the significance and effectiveness of the proposed MC-TeCF approach in terms of improving accuracy, as well as in dealing with very sparse data sets or cold start users compared with the standard Single-Criteria user-based CF approach.
Abstract
Recommender Systems are information systems that attempt to recommend items of interest to particular users based on their explicit and implicit preferences. Multi-Criteria Decision Making (MCDM) aims at assisting the decision maker in the decision making process, or giving the decision maker a recommendation, concerning a set of actions, alternatives, items etc. Thus, despite their differences, Recommender Systems and Multi-Criteria Decision Making share the same objective which is supporting the decision making process and reducing information overload. In this paper we propose a novel hybrid Multi-Criteria Trust-enhanced CF (MC-TeCF) approach. The proposed MC-TeCF approach combines the MC user-based CF and the MC user-based Trust filtering approaches to alleviate the standard Single-Criteria user-based CF limitations. Empirical results demonstrate the significance and effectiveness of the proposed MC-TeCF approach in terms of improving accuracy, as well as in dealing with very sparse data sets or cold start users compared with the standard Single-Criteria user-based CF approach.
Keywords
Computer Science
Choice Reviews OnlineData mining: concepts and techniques
28,877 Citations2012Jiawei Han, Micheline Kamber +1 more
Data mining is the search for new, valuable, and nontrivial information in large volumes of data, a cooperative effort of humans and computers that is possible to put data-mining activities into one of two categories: Predictive data mining, which produces the model of the system described by the given data set, or Descriptive data mining which produces new, nontrivials information based on the available data set.
IEEE Transactions on Knowledge and Data EngineeringToward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
10,115 Citations2005Gediminas Adomavičius, Alexander Tuzhilin
This paper presents an overview of the field of recommender systems and describes the current generation of recommendation methods that are usually classified into the following three main categories: content-based, collaborative, and hybrid recommendation approaches.
Social information filtering
2,800 Citations1995Upendra Shardanand, Pattie Maes
The implementation of a networked system called Ringo, which makes personalized recommendations for music albums and artists, and four different algorithms for making recommendations by using social information filtering were tested and compared.
Trust-aware recommender systems
1,181 Citations2007Paolo Massa, Paolo Avesani
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.
Lecture notes in computer scienceHybrid Web Recommender Systems
1,125 Citations2007Robin Burke
This chapter surveys the space of two-part hybrid recommender systems, comparing four different recommendation techniques and seven different hybridization strategies and finds that cascade and augmented hybrids work well, especially when combining two components of differing strengths.
Trust in recommender systems
860 Citations2005John O’Donovan, Barry Smyth
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.
Information RetrievalAn Empirical Analysis of Design Choices in Neighborhood-Based Collaborative Filtering Algorithms
657 Citations2002Jon Herlocker, Joseph A. Konstan +1 more
An analysis framework is applied that divides the neighborhood-based prediction approach into three components and then examines variants of the key parameters in each component, and identifies the three components identified are similarity computation, neighbor selection, and rating combination.
IEEE Intelligent SystemsNew Recommendation Techniques for Multicriteria Rating Systems
500 Citations2007Gediminas Adomavičius, YoungOk Kwon
This article proposes several new techniques for extending recommendation technologies to incorporate and leverage multicriteria rating information and improve recommendation accuracy as compared with single-rating recommendation approaches.
Lecture notes in computer scienceGenerating Predictive Movie Recommendations from Trust in Social Networks
399 Citations2006Jennifer Golbeck
This paper presents FilmTrust, a website that uses trust in web-based social networks to create predictive movie recommendations, and shows that these recommendations are more accurate than other techniques when the user's opinions about a film are divergent from the average.
Communications of the ACMPersonalization on the Net using Web mining: introduction
371 Citations2000Maurice Mulvenna, Sarabjot Singh Anand +1 more
Communications of the ACMPersonalization technologies
341 Citations2005Gediminas Adomavičius, Alexander Tuzhilin
By leveraging customer reactions to personalized products and services, companies continuously improve their personalization processes through an iterative feedback loop resulting in the `virtuous cycle' of personalization.
Maut — Multiattribute Utility Theory
262 Citations2006James S. Dyer
This chapter describes the multiattribute decision problem, and discusses the conditions that allow a multiattribute preference function to be decomposed into additive and multiplicative forms under conditions of certainty and risk.
Multi-Criteria Recommender Systems
221 Citations2015Gediminas Adomavičius, YoungOk Kwon
This chapter aims to provide an overview of the class of multi-criteria recommender systems, i.e., the category of recommender systems that use multi-criteria preference ratings, and a review of current algorithms that use multi-criteria ratings for calculating predictions and generating recommendations.
World Wide WebAnalysis and Classification of Multi-Criteria Recommender Systems
193 Citations2007Nikos Manouselis, Constantina Costopoulou
A set of dimensions that distinguish, describe and categorize multi-criteria recommender systems are identified, based on existing taxonomies and categorizations, which are integrated into an overall framework that is used for the analysis and classification of a sample of existing multi-CriteriaRecommender systems.
Multi-Criteria Recommender Systems
170 Citations2010Gediminas Adomavičius, Nikos Manouselis +1 more
This chapter aims to provide an overview of the class of multi-criteria recommender systems, and focuses on the category of multi-criteria rating recommenders – techniques that provide recommendations by modelling a user’s utility for an item as a vector of ratings along several criteria.
Trust and Recommendations
120 Citations2010Patricia Victor, Martine De Cock +1 more
This chapter discusses and illustrates the basic trust concepts such as trust and distrust modeling, propagation and aggregation, and gives an overview of state-of-the-art approaches for trust-enhanced recommender systems.
Lecture notes in computer scienceDesigning Specific Weighted Similarity Measures to Improve Collaborative Filtering Systems
98 Citations2008Laurent Candillier, Frank Meyer +1 more
It is shown that using weighted similarity measures significantly improves the results of both user- and item-based approaches, and bespoke ones, that are tailored to type of data that is typically available (i.e. very sparse), tend to lead to better results.
Lecture notes in computer scienceUsing Trust in Collaborative Filtering Recommendation
93 Citations2007Chein-Shung Hwang, Yu‐Pin Chen
An improved mechanism to the standard CF techniques by incorporating trust into CF recommendation process is presented, which derives the trust score directly from the user rating data and exploits the trust propagation in the trust web.
Lecture notes in business information processingA Multi-criteria Collaborative Filtering Approach for Research Paper Recommendation in Papyres
56 Citations2009Amine Naak, Hicham Hage +1 more
Papyres employs a Hybrid recommender system that combines both Content-based and Collaborative filtering to help researchers locate research material, and a multi-criteria approach is used to evaluate the articles, allowing researchers to denote their interest in specific parts of articles.
UTA-Rec
52 Citations2008Kleanthi Lakiotaki, Stelios Tsafarakis +1 more
The results indicate that the proposed Multiple Criteria Analysis methodology can certainly improve the recommendation process by producing highly accurate results, from a user oriented perspective.
Lecture notes in computer scienceIntelligent Techniques for Web Personalization
47 Citations2005Sarabjot Singh Anand, Bamshad Mobasher
This chapter provides a comprehensive overview of the topic of Intelligent Techniques for Web Personalization, and describes the various sources of data available to personalization systems, the modelling approaches employed and the current approaches to evaluating these systems.
A Framework of Hybrid Recommendation System for Government-to-Business Personalized E-Services
18 Citations2010Qusai Y. Shambour, Jie Lü
This study presents a personalized hybrid recommender system framework to handle personalized recommendations in G2B e- services, in particular, business partner matching e-services which employs a hybrid trust-based multi-criteria recommendation model which integrates the techniques of trust- based filtering with the multi-Criteria CF.
Personalization Beyond Recommender Systems
6 Citations2007Petra Schubert, Uwe Leimstoll +1 more
The main contribution described in this paper is the Personalization Map, which provides an extensive overview on personalization functions that can be used to individualize and improve human-computer-interaction both in B2C and B2B e-commerce environments.