Year: 2024
Type: article
Abstract: The article offers a comparison between Tesserae (a text-reuse detection tool) and cosine similarity (used here as a measure of similarity between texts) and assesses their applicability to tracking textual affinities of different versions of historical texts on the basis of Early Modern English versions of Psalm 6 found in publications printed between 1530 and 1557. It is shown that cosine similarity is a better tool for the task of identifying and measuring the level of similarity between texts. At the same time, the article argues that cosine similarity measurements should be performed on texts represented as feature vectors consisting of n-grams.
Source: Roczniki Humanistyczne
DOI: 10.18290/rh24725.9s
Author: Jerzy Wójcik
Institution: John Paul II Catholic University of Lublin
Language: English
Subfield: Literature and Literary Theory
Field: Arts and Humanities
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4405933298