Assessing Documents' Credibility with Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4333

  title =        "Assessing Documents' Credibility with Genetic
  author =       "Joao Palotti and Thiago Salles and Gisele L. Pappa and 
                 Marcos A. Goncalves and Wagner {Meira, Jr.}",
  pages =        "200--207",
  booktitle =    "Proceedings of the 2011 IEEE Congress on Evolutionary
  year =         "2011",
  editor =       "Alice E. Smith",
  month =        "5-8 " # jun,
  address =      "New Orleans, USA",
  organization = "IEEE Computational Intelligence Society",
  publisher =    "IEEE Press",
  ISBN =         "0-7803-8515-2",
  keywords =     "genetic algorithms, genetic programming, authorship,
                 automatic document classification, citations,
                 classifier, document credibility assessing, structural
                 metrics, citation analysis, document handling, pattern
  DOI =          "doi:10.1109/CEC.2011.5949619",
  abstract =     "The concept of example credibility evaluates how much
                 a classifier can trust an example when building a
                 classification model. It is given by a credibility
                 function, estimated according to a series of factors
                 that influence the credibility of the examples, and is
                 context- dependent. Here we deal with automatic
                 document classification, and study the credibility of a
                 document according to three factors: content,
                 authorship and citations. We propose a genetic
                 programming algorithm to estimate the credibility of
                 training examples, which is then added to a
                 credibility-aware classifier. For that, we model the
                 authorship and citation data as a complex network, and
                 select a set of structural metrics that can be used to
                 estimate credibility. These metrics are then merged
                 with other content-related ones, and used as terminals
                 for the GP. The GP was tested in a subset of the
                 ACM-DL, and results showed that the credibility-aware
                 classifier obtained results of micro and macroF_1 from
                 5percent to 8percent better than the traditional
  notes =        "CEC2011 sponsored by the IEEE Computational
                 Intelligence Society, and previously sponsored by the
                 EPS and the IET.",

Genetic Programming entries for Joao Palotti Thiago Cunha de Moura Salles Gisele L Pappa Marcos Andre Goncalves Wagner Meira