TY - JOUR
T1 - Using machine learning to assess rape reports
T2 - Sentiment analysis detection of officers' “signaling” about victims' credibility
AU - Lovell, Rachel E.
AU - Klingenstein, Joanna
AU - Du, Jiaxin
AU - Overman, Laura
AU - Sabo, Danielle
AU - Ye, Xinyue
AU - Flannery, Daniel J.
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/9/1
Y1 - 2023/9/1
N2 - Purpose: The first of two articles from a larger study whose aim was to teach a computer to detect innuendo (or signaling) about a victim's credibility in incident reports of rape. This study explored the degree of sentiment and subjectivity in the reports and whether these predicted case progression and outcomes. Methods: We employed machine learning, specifically sentiment analysis to assess sentiment (opinion) and subjectivity of textual content. The sample consists of 5638 incident reports of rape with a sexual assault kit from a U.S., urban Midwestern jurisdiction. Results: Sentiment was detected, tended to skew near neutral/slightly negative and more subjective, and predicted case progression and outcomes, but was not quite what was expected. Conclusions: We taught a computer to detect signaling via tone that predicted case progression and outcomes. Findings indicate that the cases recommended for prosecution were longer and had positive sentiment and positive subjectivity. Cases not recommended for prosecution were shorter with more neutral statements of “fact” or observations. Implications and recommendations for improved, less biased report writing are provided.
AB - Purpose: The first of two articles from a larger study whose aim was to teach a computer to detect innuendo (or signaling) about a victim's credibility in incident reports of rape. This study explored the degree of sentiment and subjectivity in the reports and whether these predicted case progression and outcomes. Methods: We employed machine learning, specifically sentiment analysis to assess sentiment (opinion) and subjectivity of textual content. The sample consists of 5638 incident reports of rape with a sexual assault kit from a U.S., urban Midwestern jurisdiction. Results: Sentiment was detected, tended to skew near neutral/slightly negative and more subjective, and predicted case progression and outcomes, but was not quite what was expected. Conclusions: We taught a computer to detect signaling via tone that predicted case progression and outcomes. Findings indicate that the cases recommended for prosecution were longer and had positive sentiment and positive subjectivity. Cases not recommended for prosecution were shorter with more neutral statements of “fact” or observations. Implications and recommendations for improved, less biased report writing are provided.
KW - Attrition
KW - Natural language processing
KW - Sentiment analysis
KW - Sexual assault, machine learning
KW - Signaling
KW - Victim credibility
UR - http://www.scopus.com/inward/record.url?scp=85169065471&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85169065471&partnerID=8YFLogxK
U2 - 10.1016/j.jcrimjus.2023.102106
DO - 10.1016/j.jcrimjus.2023.102106
M3 - Article
AN - SCOPUS:85169065471
SN - 0047-2352
VL - 88
JO - Journal of Criminal Justice
JF - Journal of Criminal Justice
M1 - 102106
ER -