Study at CFL





Krzysztof Kredens, IFL, Aston
Validity in forensic authorship analysis

The development of powerful computing tools and easy accessibility of large quantities of language data online have sparked renewed interest in authorship analysis in a variety of domains. However, as new computational models are put forward for authorship attribution purposes and ever greater success rates reported, a vast majority of the studies remain silent on the nature and types of linguistic phenomena associated with idiolectal style. Meanwhile, in forensic authorship attribution, models should be explanatorily rich: the forensic linguist needs to be both certain of the validity of his/her findings and able to explain them to lay triers of fact; s/he needs to know what actually happens inside the black box.

This presentation reports on the findings of an experiment using a very large corpus created specifically for authorship analysis purposes. However, the experiment was less concerned with classification results but focused instead on validity issues, and so looked at the kinds of style markers responsible for correct author classification within the corpus. The question of why the particular markers performed well will also be addressed.


Centre for Forensic Linguistics, Aston University, Birmingham, UK, 2018