@article {savoy_authorship_2013,
	title = {Authorship attribution based on a probabilistic topic model},
	journal = {Information Processing \& Management},
	volume = {49},
	number = {1},
	year = {2013},
	note = {00009},
	pages = {341{\textendash}354},
	abstract = {In this article, Jacques Savoy tested the efficiency and reliability of using LDA (Latent Dirichlet Analysis) as a means of author attribution. Savoy opens the article by discussing the basic components of author attributions: a frequent word data set and a distance measurement. Noting that there is a limited number of test corpora for authorship attribution, Savoy compiles and describes the two test corpora used in his study: selections from English language publication the Glasgow Herald and selections from Italian language publication La Stompa. Savoy conducts authorship attribution tests on these data sets using delta, chi-sqaure, Kullback-Leibler, and Naive Bayes calculations as well as the LDA. While LDA is generally used to categorize texts into topics, Savoy concludes that it can be useful for authorship attribution. },
	keywords = {Authorship attribution, Lexical statistics, Machine learning, Text categorization},
	issn = {0306-4573},
	doi = {10.1016/j.ipm.2012.06.003},
	url = {http://www.sciencedirect.com/science/article/pii/S0306457312000751},
	author = {Savoy, Jacques}
}