Cognitive processing of facial affect: connectionist model of deviations in schizophrenia.

Connectionist-model simulations of competing hypotheses of cognition in schizophrenia were constructed and tested. Emphasis was placed on judgment of affect, a prominent area of disturbance in this disorder with potential implications for social impairment. Participants with paranoid or nonparanoid schizophrenia and control participants provided judgments of affect as expressed in photographic faces. Schizophrenia groups were less accurate than control groups, and the paranoid group had greater latencies than did other groups. Model predictions simultaneously addressed judgment content and latencies for each trial. Results provide a connectionist extension of an account of deficits in schizophrenia that originated at the computational (stochastic modeling) level of analysis. This account postulates extra stages of item encoding but no reduction in formally defined processing capacity. It also provides for abnormalities in both judgment patterns and duration and is consistent with biological accounts of schizophrenia deficits. The substantive findings are supported by strategic innovations in the construction and testing of connectionist models.