Real-world, high-stakes deceptive speech: Theoretical validation and an examination of its potential for detection automation.

摘要

The study of deception and the theories which have been developed have relied heavily on laboratory experiments, in controlled environments, utilizing American college students, participating in mock scenarios. The goal of this study was to validate previous deception research in a real-world high-stakes environment. An additional focus of this study was the development of procedures to process data (e.g. video or audio recordings) from real-world environments in such a manner that behavioral measures can be extracted and analyzed. This study utilized previously confirmed speech cues and constructs to deception in an attempt to validate a leading deception theory, Interpersonal Deception Theory (IDT). Several measures and constructs, utilized and validated in existing research, were explored and validated in this study. The data analyzed came from an adjudicated real-world high-stakes criminal case in which the subject was sentenced in federal court to 470 years in prison for creating child pornography, rape, sexual exploitation of children, child sexual assault and kidnapping; a crime spree that spanned over a five years and four states. The results did validate IDT with mixed results on individual measures and their constructs. The exploratory nature of the study, the volume of data, and the numerous methods of analysis used generated many possibilities for future research.