Modeling conditional dependencies between recidivism and cognitive emotion regulation strategies among prisoners using a Bayesian network with interpretable summary indexes

Emotion regulation is widely recognized as a critical factor in offender rehabilitation and recidivism reduction. However, empirical research has not yet clarified how distinct patterns of cognitive emotion regulation strategies (CERS) relate to recidivism across different types of criminal offenses. We therefore constructed a Bayesian network to model the probabilistic relationships between CERS and recidivism, conditioning on crime type. To obtain a practical, parsimonious network, we first derived interpretable summary indexes from multiple CERS indicators using convex generalized structured component analysis and used these indexes as network nodes. The resulting network suggested that CERS may vary across crime types and are differentially associated with the conditional probability of recidivism. These findings highlight the potential value of considering both individual CERS profiles and crime type in future research on correctional assessment and intervention planning.