Authorship Verification by combining SVMs with Kernels Optimized for Different Feature Categories

@inproceedings{SolrzanoSoto2015AuthorshipVB,
  title={Authorship Verification by combining SVMs with Kernels Optimized for Different Feature Categories},
  author={Juli{\'a}n Sol{\'o}rzano-Soto and Victor Mijangos and Alejandro Pimentel and Fernanda L{\'o}pez-Escobedo and Azucena Montes Rend{\'o}n and Gerardo Sierra},
  booktitle={CLEF},
  year={2015}
}
We present our approach to the PAN-2015 authorship verification task. We combine one-class SVM classifiers under the hypothesis that different categories of features a) are better suited for different authors and b) have different underlying topologies. Thus, we have each classifier operate in a different feature subset with a different kernel function, and the output is used to train a logistic regression model which assigns a different weight to each category of features. Results show that… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Similar Papers

Loading similar papers…