Decision support for determining veracity via linguistic-based cues

摘要

Deception detection is an essential skill in careers such as law enforcement and must be accomplished accurately. However, humans are not very competent at determining veracity without aid. This study examined automated text-based deception detection which attempts to overcome the shortcomings of previous credibility assessment methods. A real-world, high-stakes sample of statements was collected and analyzed. Several different sets of linguistic-based cues were used as inputs for classification models. Overall accuracy rates of up to 74% were achieved, suggesting that automated deception detection systems can be an invaluable tool for those who must assess the credibility of text.