Lie-Detecting Software Developed Using Court Data

Advertisement
By Indo-Asian News Service | Updated: 10 December 2015 18:19 IST
Lie-Detecting Software Developed Using Court Data
By studying videos from high-stakes court cases, researchers from University of Michigan have built a prototype of a lie-detecting software based on real-world data.

The prototype considers both the speaker's words and gestures and unlike a polygraph, it does not need to touch the subject in order to work.

In experiments, it was up to 75 percent accurate in identifying who was being deceptive (as defined by trial outcomes), compared with humans' scores of just above 50 percent.

With the software, the researchers say they have identified several lies.

"Lying individuals moved their hands more. They tried to sound more certain. And, somewhat counterintuitively, they looked their questioners in the eye a bit more often than those presumed to be telling the truth, among other behaviours," the authors noted.

Advertisement

"There are clues that humans give naturally when they are being deceptive, but we're not paying close enough attention to pick them up. We're not counting how many times a person says 'I' or looks up. We're focusing on a higher level of communication," explained Rada Mihalcea, professor of computer science and engineering who leads the project.

The system might one day be a helpful tool for security agents, juries and even mental health professionals.

Advertisement

To develop the software, the team used machine-learning techniques to train it on a set of 120 video clips from media coverage of actual trials.

The videos include testimony from both defendants and witnesses.

Advertisement

In half of the clips, the subject is deemed to be lying. To determine who was telling the truth, the researchers compared their testimony with trial verdicts.

The researchers fed the data into their system and let it sort the videos.

When it used input from both the speaker's words and gestures, it was 75 percent accurate in identifying who was lying.

For this work, the researchers themselves classified the gestures, rather than having the computer do it. They are in the process of training the computer to do that.

A paper on the findings was presented at the international conference on multimodal interaction and is published in the 2015 conference proceedings.

 

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.

Further reading: Apps, Science, Software
Advertisement

Related Stories

Popular Mobile Brands
  1. Vivo X200 FE Allegedly Spotted on Geekbench With This MediaTek Chipset
  2. Vivo Y400 Pro 5G Confirmed to Launch in India Soon, Design Teased
  3. OnePlus Bullets Wireless Z3 to Launch in India on June 19: All Details
  4. Apple's M4 Mac Mini Price in India Drops to Rs. 49,999 With These Discounts
  1. Apple's Mac Mini With M4 Chip Price in India Drops to Rs. 49,999 With Discounts on Amazon
  2. Samsung Galaxy M36, Galaxy F36 Spotted on Google Play Console; Galaxy M36 Launch Reportedly Teased via Amazon
  3. Google, Scale AI's Largest Customer, Said to Plan Split After Meta Deal
  4. SpaceX Launches 26 New Starlink Satellites, Expands Global Internet Network
  5. Aurora Alert! Northern Lights May Be Visible as Far South as New York on June 14
  6. New Island Forms in Caspian Sea as Water Levels Drop, Russian Scientists Confirm
  7. Kesari Chapter 2 Now Streaming on JioHotstar: Everything You Need to Know About Akshay Kumar Starrer Movie
  8. Steam for Mac Now Available as Native Apple Silicon App With Latest Beta Release
  9. Coinbase Announces American Express-Backed Crypto Credit Card That Offers Bitcoin Rewards
  10. Killed by Google: Support for Android Instant Apps to Reportedly Be Dropped Later This Year
Gadgets 360 is available in
Download Our Apps
Available in Hindi
© Copyright Red Pixels Ventures Limited 2025. All rights reserved.