Reflecting on Our SBP-BRiMS 2025 Best Paper Award
Published:
I’m proud to share that our paper, “Evaluating Visual and Behavioral Signals of Deception in Real-World Contexts,” received the Best Paper Award at SBP-BRiMS 2025. I coauthored the work with Hoorad Abootalebi, Georgia Ng Wai, and Tempestt Neal.
The study examined visual and behavioral signals used in deception detection across biographical, academic, well-being, and crime-related topics. The usefulness of cues and model performance varied across these contexts. That variation is central to the contribution: evaluating a model in one setting does not tell us how its signals will perform in another. Context needs to be part of how we assess these systems and interpret their outputs.
This recognition is especially meaningful because Georgia’s contributions grew out of her undergraduate research. I’m grateful to my coauthors and collaborators for the care and expertise they brought to this work, and to the SBP-BRiMS community for recognizing it.
Paper abstract
Deception detection remains a critical challenge for security, human-centered computing, and behavioral research, yet most existing systems struggle to generalize across real-world contexts. This paper examines multimodal deception detection across four domains—academics, biography, well-being, and crime. Using 400 videos from two datasets, including a new one we have released, we evaluate facial, affective, gaze, and gesture features in single- and cross-domain settings. Gaze and gesture consistently outperform facial and affective features, especially in high-risk or narrative contexts, despite being selected less often. Facial features, though common, often lack predictive value, underscoring the need to prioritize performance over frequency. We find that expressivity, not response length, improves detectability, and generalization is stronger when domains share risk or narrative structure. These insights support the design of adaptable, context-aware deception detection systems.