Friday, March 1, 2013

Computer Assisted Deception Detection


One of the courts key functions is determining "the truth" in testimony.  There is work being done to provide automated assistance.


---
Two recent articles have brought the possibility that automated deception detection may be coming to our courts in the near future.

First, a January 2013 Wired Magazine article describes work being done for the US Department of Homeland Security Border Patrol to develop an automated kiosk described as:
"The Interrogation Bot:
Just three sensors tell the Embodied Avatar kiosk everything it needs to know about whether someone is telling the truth. An infrared camera records eye movement and pupil dilation at up to 250 frames per second—the stress of lying tends to cause the pupils to dilate. A high-definition video camera captures fidgets such as shrugging, nodding, and scratching, which tend to increase during a deceptive statement. And a microphone collects vocal data, because lies often come with minute changes in pitch. Future versions of the machine might go even further—a weight-sensing platform could measure leg and foot shifts or toe scrunches, and a 3-D camera could track the movements of a person’s entire body."
The other paper that appeared recently is titled "Automatic deception detection in Italian court cases" by Tommaso Fornaciari and Massimo Poesio.  The paper abstract states:
"Effective methods for evaluating the reliability of statements issued by witnesses and defendants in hearings would be an extremely valuable support to decision-making in court and other legal settings. In recent years, methods relying on stylometric techniques have proven most successful for this task; but few such methods have been tested with language collected in real-life situations of high-stakes deception, and therefore their usefulness outside lab conditions still has to be properly assessed. In this study we report the results obtained by using stylometric techniques to identify deceptive statements in a corpus of hearings collected in Italian courts. The defendants at these hearings were condemned for calumny or false testimony, so the falsity of (some of) their statements is fairly certain. In our experiments we replicated the methods used in previous studies but never before applied to high-stakes data, and tested new methods. We also considered the effect of a number of variables including in particular the homogeneity of the dataset. Our results suggest that accuracy at deception detection clearly above chance level can be obtained with real-life data as well."
Last, I have heard of other automated decision support aides that are also being worked on currently.  It is a very interesting time now as the fruits of initial automation work and infrastructure are just now starting to be realized.

No comments:

Post a Comment