Combating Web Spam with TrustRank

By Zoltán Gyöngyi, Hector Garcia-Molina, Jan O. Pedersen. 2004

1,287 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

Attacking Graph-based Classification via Manipulating the Graph Structure (2019, methodology): “r reputation scores, assign/learn the edge weights, and propagate the prior reputation scores. In particular, state-of-the-art collective classification methods include Random Walk (RW) based methods [9, 10, 30, 36, 40, 72, 74, 76], Loopy Belief Propagation (LBP) based methods [1, 14, 23, 25, 47, 59”
Fast Incremental and Personalized PageRank (2010, methodology): “In this paper, we focus on (incremental) computation of PageRank [39], personalized PageRank [14,19,39], SALSA [30], and personalized SALSA [38, 40].”
An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation (2010, background): “Examples include spam detection [23], topic-oriented crawling [24], keyword searching in relational databases [25], and measuring citation impact factor [26].”
A survey of trust in computer science and the Semantic Web (2007, background): “Given a small data set of decisions made by users about whether or not Web sites are spam, TrustRank [86] uses the link structure to other pages to determine whether or not they are also spam.”
Aiding the Detection of Fake Accounts in Large Scale Social Online Services (2012, methodology): “EigenTrust improves over PageRank [45], and uses the same basic mechanism as TrustRank [30].”
Mathematical properties and analysis of Google's PageRank (2008, background): “The personalization vector v can be used to combat link spamming [7].”
Web Spam Taxonomy (2005, methodology): “For instance, the spam detection methods presented in [5] take advantage of the approximate isolation of reputable, non-spam pages: reputable web pages seldom point to spam.”
Augmenting web pages and search results to support credibility assessment (2011, methodology): “Two of the better known algorithms, TrustRank [16] and CredibleRank [4], use the link structure of the Web to determine a credibility score.”
GOTCHA! Network-Based Fraud Detection for Social Security Fraud (2017, methodology): “…fraud X X X 8 (Wang and Chiu 2008) online auction fraud X X 9 (Akoglu et al. 2010) various X 10 (Yanchun et al. 2011) online auction fraud X 11 (Gyöngyi et al. 2004) web spam X X 12 (Chiu et al. 2011) online auction fraud X 13 (Chau et al. 2006) online auction fraud X X X 14 (Pandit et al.…”
ItemRank: A Random-Walk Based Scoring Algorithm for Recommender Engines (2007, methodology): “…PageRank has been analysed in [Langville and Meyer, 2003] and custom static score distribution vectors d have been applied to compute topic-sensitive PageRank [Haveliwala, 2002], reputation of a node in a peerto-peer network [Kamvar et al., 2003b] and for combating web spam [Gyongyi et al., 2004].”
Learning to Rank for Information Retrieval and Natural Language Processing (2011, neutral): “Spam score Document likelihood of spam page [45] Page quality score Document likelihood of low quality page [10]”
Automatic identification of user goals in Web search (2005, background): “We did not observe any noticeable noise from link spams or mirror sites for our benchmark queries, but existing techniques for spam and mirror detection [18, 19, 20, 21] may be used to avoid any potential issue.”
LETOR: Benchmark Dataset for Research on Learning to Rank for Information Retrieval (2007, methodology): “These include document retrieval [3], collaborative filtering [14], key term extraction [8], definition finding [32], important email routing [4], sentiment analysis [26], product rating [9], and anti web spam [13].”