An Automata Based Authorship Identification System

Authors:
Tsau Young Lin;Shangxuan Zhang
Affiliations:
Department of Computer Science, San Jose State University, San Jose, USA 95192;Department of Computer Science, San Jose State University, San Jose, USA 95192
Venue:
New Frontiers in Applied Data Mining
Year:
2009

Citing 5
Cited 0

Stochastic Grammatical Inference of Text Database Structure

Machine Learning
Introduction to Automata Theory, Languages and Computability

Introduction to Automata Theory, Languages and Computability
Learning Stochastic Regular Grammars by Means of a State Merging Method

ICGI '94 Proceedings of the Second International Colloquium on Grammatical Inference and Applications
Patterns in Numerical Data: Practical Approximations to Kolmogorov Complexity

RSFDGrC '99 Proceedings of the 7th International Workshop on New Directions in Rough Sets, Data Mining, and Granular-Soft Computing
A Fast Automaton-Based Method for Detecting Anomalous Program Behaviors

SP '01 Proceedings of the 2001 IEEE Symposium on Security and Privacy

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper uses the learning capability of finite automata to develop an authorship identification system. Based on ALERGIA algorithm, we use writing samples of an author to build a stochastic finite automaton. This automaton represents the writing characteristics of the author. This automaton, then, can be used to test whether an anonymous writing piece belongs to this author. Initial tests are quite successful.