EUVIMEDEUVIMED entdecken
Open Access

Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation

Sverker Sikstrom iD, Mats Dahl iD, Emma Claesdotter-Knutsson iD

Journal of Medical Internet Research · 2023

DOI: 10.2196/43499 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, 2023. Verfasst von Sverker Sikstrom und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, Lund, Sweden. Hauptthemen laut MEDLINE: Intimate Partner Violence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

To support a victim of violence and establish the correct penalty for the perpetrator, it is crucial to correctly evaluate and communicate the severity of the violence. Recent data have shown these communications to be biased. However, computational language models provide opportunities for automated evaluation of the severity to mitigate the biases.

Objective

We investigated whether these biases can be removed with computational algorithms trained to measure the severity of violence described.

Methods

In phase 1 (P1), participants (N=71) were instructed to write some text and type 5 keywords describing an event where they experienced physical violence and 1 keyword describing an event where they experienced psychological violence in an intimate partner relationship. They were also asked to rate the severity. In phase 2 (P2), another set of participants (N=40) read the texts and rated them for severity of violence on the same scale as in P1. We also quantified the text data to word embeddings. Machine learning was used to train a model to predict the severity ratings.

Results

For physical violence, there was a greater accuracy bias for humans (r2=0.22) compared to the computational model (r2=0.31; t38=–2.37, P=.023). For psychological violence, the accuracy bias was greater for humans (r2=0.058) than for the computational model (r2=0.35; t38=–14.58, P

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Intimate Partner ViolenceHumansViolenceSexual BehaviorSexual PartnersCommunication

Stichwörter der Autor:innen

debiasingmachine learningnatural language processingphysicalpsychologicalviolence

Autor:innen und Institutionen

  • Department of Psychology, Lund, Sweden.
  • Child and Adolescent Psychiatry, Department of Clinical Sciences Lund, Lund University, Lund, Sweden.
  • Department of Child and Adolescent Psychiatry, Skåne University Hospital, Lund, Sweden.

ORCID-Profile: Sverker Sikstrom, Mats Dahl, Emma Claesdotter-Knutsson

Zitieren

APA

Sikstrom, S., Dahl, M., & Claesdotter-Knutsson, E. (2023). Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation. Journal of Medical Internet Research. https://doi.org/10.2196/43499

Vancouver

Sikstrom S, Dahl M, Claesdotter-Knutsson E. Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation. Journal of Medical Internet Research. 2023. doi:10.2196/43499

BibTeX
@article{Sikstrom2023,
  author = {Sikstrom, Sverker and Dahl, Mats and Claesdotter-Knutsson, Emma},
  title = {Removing Biases in Communication of Severity Assessments of Intimate Partner Violence: Model Development and Evaluation},
  journal = {Journal of Medical Internet Research},
  year = {2023},
  doi = {10.2196/43499}
}
Kostenlos starten →