Cargando…

Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics

Through advances in neural language modeling, it has become possible to generate artificial texts in a variety of genres and styles. While the semantic coherence of such texts should not be over-estimated, the grammatical correctness and stylistic qualities of these artificial texts are at times rem...

Descripción completa

Detalles Bibliográficos
Autores principales: Karsdorp, Folgert, Manjavacas, Enrique, Kestemont, Mike
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6804983/
https://www.ncbi.nlm.nih.gov/pubmed/31639170
http://dx.doi.org/10.1371/journal.pone.0224152
_version_ 1783461300168294400
author Karsdorp, Folgert
Manjavacas, Enrique
Kestemont, Mike
author_facet Karsdorp, Folgert
Manjavacas, Enrique
Kestemont, Mike
author_sort Karsdorp, Folgert
collection PubMed
description Through advances in neural language modeling, it has become possible to generate artificial texts in a variety of genres and styles. While the semantic coherence of such texts should not be over-estimated, the grammatical correctness and stylistic qualities of these artificial texts are at times remarkably convincing. In this paper, we report a study into crowd-sourced authenticity judgments for such artificially generated texts. As a case study, we have turned to rap lyrics, an established sub-genre of present-day popular music, known for its explicit content and unique rhythmical delivery of lyrics. The empirical basis of our study is an experiment carried out in the context of a large, mainstream contemporary music festival in the Netherlands. Apart from more generic factors, we model a diverse set of linguistic characteristics of the input that might have functioned as authenticity cues. It is shown that participants are only marginally capable of distinguishing between authentic and generated materials. By scrutinizing the linguistic features that influence the participants’ authenticity judgments, it is shown that linguistic properties such as ‘syntactic complexity’, ‘lexical diversity’ and ‘rhyme density’ add to the user’s perception of texts being authentic. This research contributes to the improvement of the quality and credibility of generated text. Additionally, it enhances our understanding of the perception of authentic and artificial art.
format Online
Article
Text
id pubmed-6804983
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-68049832019-11-02 Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics Karsdorp, Folgert Manjavacas, Enrique Kestemont, Mike PLoS One Research Article Through advances in neural language modeling, it has become possible to generate artificial texts in a variety of genres and styles. While the semantic coherence of such texts should not be over-estimated, the grammatical correctness and stylistic qualities of these artificial texts are at times remarkably convincing. In this paper, we report a study into crowd-sourced authenticity judgments for such artificially generated texts. As a case study, we have turned to rap lyrics, an established sub-genre of present-day popular music, known for its explicit content and unique rhythmical delivery of lyrics. The empirical basis of our study is an experiment carried out in the context of a large, mainstream contemporary music festival in the Netherlands. Apart from more generic factors, we model a diverse set of linguistic characteristics of the input that might have functioned as authenticity cues. It is shown that participants are only marginally capable of distinguishing between authentic and generated materials. By scrutinizing the linguistic features that influence the participants’ authenticity judgments, it is shown that linguistic properties such as ‘syntactic complexity’, ‘lexical diversity’ and ‘rhyme density’ add to the user’s perception of texts being authentic. This research contributes to the improvement of the quality and credibility of generated text. Additionally, it enhances our understanding of the perception of authentic and artificial art. Public Library of Science 2019-10-22 /pmc/articles/PMC6804983/ /pubmed/31639170 http://dx.doi.org/10.1371/journal.pone.0224152 Text en © 2019 Karsdorp et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Karsdorp, Folgert
Manjavacas, Enrique
Kestemont, Mike
Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title_full Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title_fullStr Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title_full_unstemmed Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title_short Keepin’ it real: Linguistic models of authenticity judgments for artificially generated rap lyrics
title_sort keepin’ it real: linguistic models of authenticity judgments for artificially generated rap lyrics
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6804983/
https://www.ncbi.nlm.nih.gov/pubmed/31639170
http://dx.doi.org/10.1371/journal.pone.0224152
work_keys_str_mv AT karsdorpfolgert keepinitreallinguisticmodelsofauthenticityjudgmentsforartificiallygeneratedraplyrics
AT manjavacasenrique keepinitreallinguisticmodelsofauthenticityjudgmentsforartificiallygeneratedraplyrics
AT kestemontmike keepinitreallinguisticmodelsofauthenticityjudgmentsforartificiallygeneratedraplyrics