Is trust robust?: an analysis of trust-based recommendation

@inproceedings{ODonovan2006IsTR,
  title={Is trust robust?: an analysis of trust-based recommendation},
  author={John O'Donovan and Barry Smyth},
  booktitle={IUI},
  year={2006}
}
Systems that adapt to input from users are susceptible to attacks from those same users. Recommender systems are common targets for such attacks since there are financial, political and many other motivations for influencing the promotion or demotion of recommendable items [2].Recent research has shown that incorporating trust and reputation models into the recommendation process can have a positive impact on the accuracy and robustness of recommendations. In this paper we examine the effect of… CONTINUE READING

Figures, Results, and Topics from this paper.

Key Quantitative Results

  • By selecting the users which receive recommendations during the trust building process according to metrics such as the time a user pro.le has been in the system, the diversity and the reliability of the pro.les for instance, we show that we can lower the prediction shift for an attacked item to less than that of the standard benchmark technique, with our best performing technique reducing the prediction shift for an attacked item by 75%.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 39 CITATIONS

The Role of Trust in Collaborative Filtering

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Shilling attacks against recommender systems: a comprehensive survey

  • Artificial Intelligence Review
  • 2012
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Sequence-based trust in collaborative filtering for document recommendation

  • Int. J. Hum.-Comput. Stud.
  • 2011
VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Utilizing Dynamics Patterns of Trust for Recommendation System

  • 2017 International Conference on Intelligent Environments (IE)
  • 2017
VIEW 1 EXCERPT
CITES BACKGROUND

Robust Collaborative Recommendation

  • Recommender Systems Handbook
  • 2015
VIEW 2 EXCERPTS
CITES BACKGROUND

Learning with social media

VIEW 1 EXCERPT
CITES BACKGROUND