Abstract | ||
---|---|---|
Collaborative filtering (CF) based recommender systems are vulnerable to shilling attacks. In some leading e-commerce sites, there exists a large number of unlabeled users, and it is expensive to obtain their identities. Existing research efforts on shilling attack detection fail to exploit these unlabeled users. In this article, Semi-SAD, a new semi-supervised learning based shilling attack detection algorithm is proposed. Semi-SAD is trained with the labeled and unlabeled user profiles using the combination of naïve Bayes classifier and EM-», augmented Expectation Maximization (EM). Experiments on MovieLens datasets show that our proposed Semi-SAD is efficient and effective. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1145/2043932.2043985 | RecSys |
Keywords | Field | DocType |
unlabeled user profile,shilling attack detection,augmented expectation maximization,proposed semi-sad,unlabeled user,movielens datasets,existing research effort,bayes classifier,shilling attack detection algorithm,shilling attack,semi supervised learning,expectation maximization,information systems,e commerce,collaborative filtering,recommender system,em | Information system,Recommender system,Data mining,Collaborative filtering,Semi-supervised learning,Naive Bayes classifier,Computer science,Expectation–maximization algorithm,MovieLens,Exploit,Artificial intelligence,Machine learning | Conference |
Citations | PageRank | References |
11 | 0.54 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiang Wu | 1 | 359 | 37.24 |
Jie Cao | 2 | 627 | 73.36 |
Bo Mao | 3 | 16 | 5.03 |
Youquan Wang | 4 | 57 | 5.72 |