Genetic Heuristic Development: Feature selection for author identification

Abstract

Author identification is the process of recognizing an author based on a sample of text. Feature selection is the process of selecting the most salient features required for recognition. In many cases, this results in an increase in recognition accuracy. In this paper, we apply Genetic and Evolutionary Feature Selection with Machine Learning (GEFeS ML ) to author identification. We then introduce Genetic Heuristic Development (GHD), a process to improve the matching process. GHD uses subsets of features found by GEFeS ML to create a high performing heuristic for feature selection.This technique successfully increases recognition accuracy while significantly reducing the number of features required for recognition.

The Best Way to a Strong Defense is a Strong Offense: Mitigating Deanonymization Attacks via Iterative Language Translation

“…The validation set was used for cross-validation in an effort to reduce overfitting [16]. GEFeS was an instance of a Steady-State Genetic Algorithm implemented in X-TOOLSS [15], [19]. GEFeS evolved a population of 20 FMs.…”