Authorship attribution of ancient texts written by ten Arabic travelers using character N-Grams

In this paper the authors investigate the authorship of some old Arabic books that are written by ten ancient Arabic travelers. Hence, several experiments of authorship attribution are conducted on these Arabic texts, by using different features such as characters, character-bigrams, character-trigrams and character-tetragrams. Furthermore, four different classifiers are employed, namely: Stamatatos distance, Manhattan distance, Multi Layer Perceptron (MLP) and Support Vector Machines (SVM). For the evaluation task, several experiments of authorship attribution, using those features and classifiers, are conducted on the Arabic dataset (called AAAT), which contains 3 short texts from every book. Results show good authorship attribution performances with an optimal score of 90% of good attribution. Moreover, this investigation has revealed interesting results concerning the Arabic language.