Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives
This work addresses the societal impact of crime reporting on public perceptions, but it is incremental as it builds on existing methods for text analysis.
The researchers tackled the problem of how language in crime reports influences readers' subjective guilt assessments by creating the SuspectGuilt Corpus with annotations, and they showed that predictive models trained on this data benefit from genre pretraining and joint supervision, achieving improved performance.
Crime reporting is a prevalent form of journalism with the power to shape public perceptions and social policies. How does the language of these reports act on readers? We seek to address this question with the SuspectGuilt Corpus of annotated crime stories from English-language newspapers in the U.S. For SuspectGuilt, annotators read short crime articles and provided text-level ratings concerning the guilt of the main suspect as well as span-level annotations indicating which parts of the story they felt most influenced their ratings. SuspectGuilt thus provides a rich picture of how linguistic choices affect subjective guilt judgments. In addition, we use SuspectGuilt to train and assess predictive models, and show that these models benefit from genre pretraining and joint supervision from the text-level ratings and span-level annotations. Such models might be used as tools for understanding the societal effects of crime reporting.