Assessing Verbal Eyewitness Confidence Statements Using Natural Language Processing
Psychological Science · 2024
DOI: 10.1177/09567976241229028 ↗Kurz gefasst
Fachartikel in der Zeitschrift Psychological Science, 2024. Verfasst von Rachel Leigh Greenspan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Criminal Justice and Legal Studies, University of Mississippi. Hauptthemen laut MEDLINE: Natural Language Processing, Mental Recall. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 31 Literaturangaben.
Abstract (Originalsprache)
After an eyewitness completes a lineup, officers are advised to ask witnesses how confident they are in their identification. Although researchers in the lab typically study eyewitness confidence numerically, confidence in the field is primarily gathered verbally. In the current study, we used a natural language-processing approach to develop an automated model to classify verbal eyewitness confidence statements. Across a variety of stimulus materials and witnessing conditions, our model correctly classified adult witnesses’ ( N = 4,541) level of confidence (i.e., high, medium, or low) 71% of the time. Confidence-accuracy calibration curves demonstrate that the model’s confidence classification performs similarly in predicting eyewitness accuracy compared to witnesses’ self-reported numeric confidence. Our model also furnishes a new metric, confidence entropy, that measures the vagueness of witnesses’ confidence statements and provides independent information about eyewitness accuracy. These results have implications for how empirical scientists collect confidence data and how police interpret eyewitness confidence statements.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Criminal Justice and Legal Studies, University of Mississippi.
- University of Pennsylvania Carey Law School.
ORCID-Profile: Rachel Leigh Greenspan
Zitieren
APA
Greenspan, R. L., Lyman, A., & Heaton, P. (2024). Assessing Verbal Eyewitness Confidence Statements Using Natural Language Processing. Psychological Science. https://doi.org/10.1177/09567976241229028
Vancouver
Greenspan RL, Lyman A, Heaton P. Assessing Verbal Eyewitness Confidence Statements Using Natural Language Processing. Psychological Science. 2024. doi:10.1177/09567976241229028
BibTeX
@article{Greenspan2024,
author = {Greenspan, Rachel Leigh and Lyman, Alex and Heaton, Paul},
title = {Assessing Verbal Eyewitness Confidence Statements Using Natural Language Processing},
journal = {Psychological Science},
year = {2024},
doi = {10.1177/09567976241229028}
}
EUVIMED