Authorship Attribution on Imbalanced English Editorial Corpora

Abstract

Authorship attribution is one of the important problem, with many applications of practical use in the real-world. Authorship identification determines the likelihood of a piece of writing produced by a particular author by examining the other writings of that author. Every author has a unique style of writing pattern. This paper identifies the unique style of an author(s) using lexical stylometric features including function words using balanced training corpus. The present paper calculates the frequencies of the lexical based stylometric features by balancing training and test corpus on English editorial documents. The present paper compares various machine learning algorithms for the authorship attribution and achieved highest average accuracy 95.58 using Random Forest classifier and 92.59 using Multilayer Perceptron algorithms.

A review on authorship attribution in text mining

“…Accordingly, various classifiers have been examined with respect to their ability to deal with data imbalance. For example, Rao et al (2017) used lexical stylometric features with RF and achieved an average accuracy of 95.74%. Alternatively, Hadjadj and Sayoud (2021) proposed a hybrid approach based on PCA and the synthetic minority oversampling technique to improve the performance of authorship attribution on imbalanced data.…”