EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Decoding Disbelief: Using Natural Language Processing's Sentiment Analysis to Assess 24 Years of Unfounded Rape Reports Narratives

Rachel E Lovell iD, Lacey Caporale, Jiaxin Du

Behavioral Sciences & the Law · 2026

DOI: 10.1002/bsl.70020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Behavioral Sciences & the Law, 2026. Verfasst von Rachel E Lovell und 2 weiteren Autor:innen. Beteiligte Einrichtung: Criminology Research Center, Cleveland State University, Cleveland, Ohio, USA. Hauptthemen laut MEDLINE: Narration, Rape, Natural Language Processing, Crime Victims. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Institute of Justice.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rape myths, including the belief that victims frequently lie, contribute to barriers in justice, such as the disproportionate use of the “unfounded” classification—where, following an investigation, it is determined no crime occurred. This study analyzes rape report narratives tied to previously untested sexual assault kits ( N = 5638) from a large, urban Midwestern (US) jurisdiction, focusing on differences in narratives deemed unfounded or where officers expressed victim lying/doubt. Using natural language processing's sentiment analysis, we assessed tone (via polarity and subjectivity) and word counts. Results showed that unfounded narratives were shorter and more negatively written than others but did not differ in subjectivity. Victim lied/doubted narratives showed no significant difference in polarity, subjectivity, or length compared to others. These findings highlight how bias can manifest in written narratives, potentially influencing case outcomes. Addressing these biases through improved report writing and limiting the misuse of the unfounded classification is essential to support victims' pathways to justice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NarrationRapeNatural Language ProcessingCrime VictimsHumansFemaleMaleAdult

Stichwörter der Autor:innen

false reportmachine learningnatural language processingrape mythsentiment analysissexual assaultunfounded

Autor:innen und Institutionen

  • Criminology Research Center, Cleveland State University, Cleveland, Ohio, USA.
  • College of Computing, Grand Valley State University, Allendale, Michigan, USA.

ORCID-Profile: Rachel E Lovell

Förderung

  • National Institute of Justice

Zitieren

APA

Lovell, R. E., Caporale, L., & Du, J. (2026). Decoding Disbelief: Using Natural Language Processing's Sentiment Analysis to Assess 24 Years of Unfounded Rape Reports Narratives. Behavioral Sciences & the Law. https://doi.org/10.1002/bsl.70020

Vancouver

Lovell RE, Caporale L, Du J. Decoding Disbelief: Using Natural Language Processing's Sentiment Analysis to Assess 24 Years of Unfounded Rape Reports Narratives. Behavioral Sciences & the Law. 2026. doi:10.1002/bsl.70020

BibTeX
@article{Lovell2026,
  author = {Lovell, Rachel E and Caporale, Lacey and Du, Jiaxin},
  title = {Decoding Disbelief: Using Natural Language Processing's Sentiment Analysis to Assess 24 Years of Unfounded Rape Reports Narratives},
  journal = {Behavioral Sciences & the Law},
  year = {2026},
  doi = {10.1002/bsl.70020}
}
Kostenlos starten →