A decentralized recommender system for effective web credibility assessment

Abstract

An overwhelming and growing amount of data is available online. The problem of untrustworthy online information is augmented by its high economic potential and its dynamic nature, e.g. transient domain names, dynamic content, etc. In this paper, we address the problem of assessing the credibility of web pages by a decentralized social recommender system. Specifically, we concurrently employ i) item-based collaborative filtering (CF) based on specific web page features, ii) user-based CF based on friend ratings and iii) the ranking of the page in search results. These factors are appropriately combined into a single assessment based on adaptive weights that depend on their effectiveness for different topics and different fractions of malicious ratings. Simulation experiments with real traces of web page credibility evaluations suggest that our hybrid approach outperforms both its constituent components and classical content-based classification approaches.

Machine learning methods for multimedia information retrieval

“…If sufficiently many evaluators assess the same Web page, one may consider evaluator and page-based collaborative filtering [Papaioannou et al, 2012] for credibility assessment. In this setting, we face a dyadic prediction task where rich metadata is associated with both the evaluator and especially with the page.…”

“…Known results typically mine Web data on the micro level, analyzing individual comments and reviews. Recently, several attempts were made to manually label and automatically assess the credibility of Web content [Olteanu et al, 2013, Papaioannou et al, 2012. Microsoft created, among others, a reference data set [Schwarz and Morris, 2011].…”

Defending imitating attacks in web credibility evaluation systems

“…For instance, MyWOT (http:// www.mywot.com/) aggregates individual users' ratings on four aspects of web credibility: Trustworthiness, Vendor reliability, Privacy and Child Safety. In academia, similar systems were also proposed, improving the commercial counterparts from different aspects [15,13]. The performance of such systems is greatly influenced by the reliability of users' ratings.…”

“…Machine learning and natural language processing are then applied to analyze and integrate user feedback. In [13], web credibility is assessed by a decentralized social recommender system. A single credibility metric is derived by combining three components: (1) item-based collaborative filtering, which is based on the features identified from the contents of pages, (2) user-based collaborative filtering, which is based on users' social relationships and (3) web search page ranking.…”

“…Based on this finding, we argue by comparing characteristics (i.e., features) of the target page with that of known credible and non-credible pages, we are able to (to certain extent) infer the credibility of the target page. By adopting features from previous works [8,13,12], as well as exploring other sources, we divide all possible features into two categories: textual content related features and link structure related features.…”