Intelligent techniques for deception detection: a survey and critical study

Abstract

The version presented here may differ from the published version or from the version of the record. Please see the repository URL above for details on accessing the published version and note that access may require a subscription.

The tangled webs we weave: Examining the effects of CEO deception on analyst recommendations

“…However, traditional text‐based deception detection has limitations, with meta‐analysis revealing only 62%–65% accuracy (Hauch et al, 2015). While there has been skepticism about the effectiveness of these methods, our independent work has achieved an accuracy of approximately 80%, similar to or better than recent advances in ML as reported by Alaskar et al (2022). This underscores the robustness of our own ML‐based deception measure, which was developed and validated prior to these findings.…”

“…This introduces validity concerns inherent to any measure of this kind. To address these concerns we rigorously adhere to methodological best practices (Alaskar et al, 2022) and provide evidence of the measure's validity through its ability to accurately predict AAER violations, data breaches, and consumer‐related fines. Additional validation comes from a nonbusiness deception sample (medical publications and publicly available instances of deception) and a negative correlation with female CEOs, consistent with theory (Ho et al, 2015).…”

“…Given the attention deception has received within the information systems literature (Alaskar et al, 2022; Şen et al, 2020), it seems inevitable that measures like ours will be employed in practical applications. As such, we provide a word of caution for the use of this technology.…”

“…To measure deception, we leveraged literature spanning two decades, showcasing consistent links between specific language patterns and intentional deception (e.g., increased negative emotions and decreased references to self; Newman et al, 2003;Pennebaker, 2011). These patterns are subconscious and challenging to manipulate or detect without computer assistance, rendering them reliable markers of deception (Alaskar et al, 2022;Newman et al, 2003;Pennebaker, 2011). Furthermore, the linguistic patterns of deception have been consistently identified across multiple disciplines such as psychology, linguistics, communications, law, criminal justice, computer science, accounting, and finance, underscoring its reliability for measurement (Arciuli et al, 2010;Burgoon et al, 2016;Fornaciari & Poesio, 2013;Ho et al, 2016;Larcker & Zakolyukina, 2012;Ten Brinke & Porter, 2012;Toma & Hancock, 2012).…”

Detecting Deceptive Behaviours through Facial Cues from Videos: A Systematic Review

“…The 81 surveyed papers are classified according to the type of extracted features (emotional, psychological, and facial) and the kinds of machine-learning algorithms. Analogously, the survey in [16] gives an overview of automated deception detection through machine-intelligence-based techniques by providing a critical analysis of the existing tools and available datasets. The authors focused on deception detection through text, speech, and video data analysis by classifying the 100 surveyed papers according to both the research domain (i.e., psychological, professional, and computational) and the type of extracted features (verbal, non-verbal, and multimodal).…”