Deception Detection in Group Video Conversations using Dynamic Interaction Networks

Abstract

Predicting groups of people who are jointly deceptive is critical in settings such as sales pitches and negotiations. Past work on deception in videos focuses on detecting single deceivers and uses facial or visual features only. We propose the concept of Face-to Face Interaction Networks (FFINs) and Negative Interaction Networks (NINs) to model interactions within a group of people. The use of FFINs and NINs in this paper enables us to leverage network relations in predicting face-to-face deception for the first time. We will use a dataset of 185 videos from a deception-based game called Resistance for deception based prediction using FFINs. We first characterize the behavior of individuals, pairs, and groups of deceptive participants compared to non-deceptive participants. Our analysis reveals that less engaged deceivers are identified early. Moreover, pairs of deceivers tend to avoid mutual interaction and focus their attention on non-deceivers. In contrast, non-deceivers interact with everyone equally. We propose the notion of Negative Interaction Networks (NINs) and create a belief propagation neural net algorithm called BPNN based on dynamic FFINs and NINs to detect deceivers from videos that are just 1 minute long. We show that our method outperforms recent state-of-the-art computer vision, graph embedding, and ensemble methods by at least 20.9% AUROC in identifying deception from videos.

Social Interaction Data-sets in the Age of Covid-19: a Case Study on Digital Commensality

“…[7] illustrates a study in which a data-set containing conference videos was used to validate their semantic segmentation approach. Moving on to social interaction studies, [16] describes deception detection in group video conversations and points out the importance of considering such a kind of interaction, as video calls are becoming increasingly common after the Covid-19 hit. [3] recorded, through video-calls, conversations between children and their caregivers to investigate gaze, gesture, and facial expressions.…”

Lie Detection Technology of Bimodal Feature Fusion Based on Domain Adversarial Neural Networks

“…Some studies have found that facial micro-expressions such as protruding lips and symbolic gestures may be signs of lying [13,14]. Moreover, some researchers have detected lies by measuring cerebral blood flow using functional brain magnetic resonance imaging or by constructing a multichannel lie detection system based on cardiac impact signals [15,16].…”

Advances in AI for web integrity, equity, and well-being

“…These resulted in development of new methods spanning robust detection and prediction models (He et al, 2021a;Mujumdar and Kumar, 2021;Oh et al, 2022b;Verma et al, 2022c), advance natural language processing and multimodality (Verma et al, 2022b,c), graphs (Raghavendra et al, 2022;Sharma et al, 2022), and recommender systems (Oh et al, 2021(Oh et al, , 2022aShalaby et al, 2022). The applications of these methods were in web integrity and led to new findings about online health misinformation (Micallef et al, 2020(Micallef et al, , 2022Verma et al, 2022a), counter-misinformation (Micallef et al, 2020;He et al, 2023;Ma et al, 2023), hate speech (He et al, 2021b), ban evaders (Niverthi et al, 2022), and digital deception (Glenski et al, 2020;Kumar et al, 2021).…”