@inbook{5820e918fac64a6d85bb6b1c4cb5eaa6,
title = "Data mining with learner corpora Choosing classifiers for L1 detection",
abstract = "This paper discusses the usefulness of machine-learning techniques for the investigation of cross-linguistic influence in learner corpora, and focuses on an approach known as supervised classification. Within this approach, one of the challenges that researchers face is deciding which particular method - or classifier - to use for a particular task. The classification task that this paper deals with is the ability of classifiers to learn to detect native language-related patterns in samples of second language writing. The empirical portion of this paper compares 20 classifiers in relation to their ability to perform this task with second language texts written by learners from 12 different native language backgrounds on the basis of their use of words and word sequences (or n-grams).",
author = "Scott Jarvis",
note = "Publisher Copyright: {\textcopyright} 2011 John Benjamins Publishing Company. All rights reserved.",
year = "2011",
doi = "10.1075/scl.45.10jar",
language = "English (US)",
series = "Studies in Corpus Linguistics",
publisher = "John Benjamins Publishing Company",
pages = "127--154",
editor = "Fanny Meunier and {De Cock}, Sylvie and Gaetanelle Gilquin and Magali Paquot",
booktitle = "A Taste for Corpora. In honour of Sylviane Granger",
address = "Netherlands",
}