Ebook: Automatic Detection of Verbal Deception

e attempt to spot deception through its correlates in human behavior has a long history. Until
recently, these efforts have concentrated on identifying individual “cues” that might occur with deception.
However, with the advent of computational means to analyze language and other human
behavior, we now have the ability to determine whether there are consistent clusters of differences
in behavior that might be associated with a false statement as opposed to a true one. While its
focus is on verbal behavior, this book describes a range of behaviors—physiological, gestural as
well as verbal—that have been proposed as indicators of deception. An overview of the primary
psychological and cognitive theories that have been offered as explanations of deceptive behaviors
gives context for the description of specific behaviors. e book also addresses the differences
between data collected in a laboratory and “real-world” data with respect to the emotional and
cognitive state of the liar. It discusses sources of real-world data and problematic issues in its
collection and identifies the primary areas in which applied studies based on real-world data are
critical, including police, security, border crossing, customs, and asylum interviews; congressional
hearings; financial reporting; legal depositions; human resource evaluation; predatory communications
that include Internet scams, identity theft, and fraud; and false product reviews. Having
established the background, this book concentrates on computational analyses of deceptive verbal
behavior that have enabled the field of deception studies to move from individual cues to overall
differences in behavior. e computational work is organized around the features used for classification
from n-gram through syntax to predicate-argument and rhetorical structure. e book
concludes with a set of open questions that the computational work has generated.