Detecting Deception Through Facial Expressions and Language Patterns

The researchers of this study have discovered a groundbreaking approach to detecting deception through the analysis of language patterns in tandem with associated facial expressions. By analyzing Facial Action Units (AU) in video recordings of 151 dyadic conversations, the researchers were able to distinguish between truthful and deceptive communication. Using the Linguistic Inquiry and Word Count (LIWC), the researchers extracted linguistic features from transcripts and paired them with corresponding facial-feature contexts.

Through this unique framework, the researchers found that in video segments where witnesses kept their eyes wide open (high intensity of AU05 - upper lid raise), deceivers used significantly fewer 'Seeing', 'Perceptual' and 'Cognitive' words and their answers were significantly shorter than truth-tellers. This innovative approach has the potential to revolutionize the way we detect deception and improve the accuracy of interrogations and investigations.

Read the research: LIWC into the Eyes: Using Facial Features to Contextualize Linguistic Analysis in Multimodal Communication