Trust no one: evaluating trust-based filtering for recommenders

Authors:
John O'Donovan;Barry Smyth
Affiliations:
Adaptive Information Cluster, Department of Computer Science, University College Dublin, Dublin 4, Ireland;Adaptive Information Cluster, Department of Computer Science, University College Dublin, Dublin 4, Ireland
Venue:
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Year:
2005

Citing 6
Cited 5

GroupLens: an open architecture for collaborative filtering of netnews

CSCW '94 Proceedings of the 1994 ACM conference on Computer supported cooperative work
Robustness Analyses of Instance-Based Collaborative Recommendation

ECML '02 Proceedings of the 13th European Conference on Machine Learning
Improving Case-Based Recommendation: A Collaborative Filtering Approach

ECCBR '02 Proceedings of the 6th European Conference on Advances in Case-Based Reasoning
Promoting Recommendations: An Attack on Collaborative Filtering

DEXA '02 Proceedings of the 13th International Conference on Database and Expert Systems Applications
Trust in recommender systems

Proceedings of the 10th international conference on Intelligent user interfaces
Empirical analysis of predictive algorithms for collaborative filtering

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence

The influence limiter: provably manipulation-resistant recommender systems

Proceedings of the 2007 ACM conference on Recommender systems
The information cost of manipulation-resistance in recommender systems

Proceedings of the 2008 ACM conference on Recommender systems
Trustworthy knowledge diffusion model based on risk discovery on peer-to-peer networks

Expert Systems with Applications: An International Journal
Risk discovery based on recommendation flow analysis on social networks

IEA/AIE'07 Proceedings of the 20th international conference on Industrial, engineering, and other applications of applied intelligent systems
Enabling topic-level trust for collaborative information sharing

Personal and Ubiquitous Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

To be successful recommender systems must gain the trust of users. To do this they must demonstrate their ability to make reliable predictions. We argue that collaborative filtering recommendation algorithms can benefit from explicit models of trust to inform their predictions. We present one such model of trust along with a cost-benefit analysis that focuses on the classical trade-off that exists between recommendation coverage and prediction accuracy.