Identification of Truth and Deception in Text: Application of Vector Space Model to Rhetorical Structure Theory

Abstract

The paper proposes to use Rhetorical Structure Theory (RST) analytic framework to identify systematic differences between deceptive and truthful stories in terms of their coherence and structure. A sample of 36 elicited personal stories, self-ranked as completely truthful or completely deceptive, is manually analyzed by assigning RST discourse relations among a story’s constituent parts. Vector Space Model (VSM) assesses each story’s position in multi-dimensional RST space with respect to its distance to truth and deceptive centers as measures of the story’s level of deception and truthfulness. Ten human judges evaluate if each story is deceptive or not, and assign their confidence levels, which produce measures of the human expected deception and truthfulness levels. The paper contributes to deception detection research and RST twofold: a) demonstration of discourse structure analysis in pragmatics as a prominent way of automated deception detection and, as such, an effective complement to lexico-semantic analysis, and b) development of RST-VSM methodology to interpret RST analysis in identification of previously unseen deceptive texts.