52/100

Moderate evidence

GainPublished recordBusinessGood Space

It’s not what you say, but how you say it: Using artifact intelligence to detect deception in natural speech in an HR recruiting context

Truvace record
TRV-2026-2522raw data (JSON)
Version
v1Published
First published
Evidence type
Benchmark or lab evaluation
Sources
1 sourcePeer-reviewed
sha256
49dcb576d1a7…check it

Human emotions trigger physical reactions of the body that can be interpreted using artificial intelligence (AI) methods. AI-enabled detection mechanisms offer new opportunities to gain deeper understanding of human emotions. AI is already able to recognize basic emotions, such as joy, anger, or fear, but is challenged to detect complex emotions accurately, such as when someone is lying. The human voice conveys a wealth of subconscious information. This research utilizes natural language processing (NLP) to pres…

The gain

A study reports that a voice-only AI tool flagged deceptive statements with about 82% accuracy, aimed at helping HR staff who are naturally weak at spotting lies in recruitment talks.

Sources

1 on file
  1. Journal of Information Technologydoi:10.1177/02683962261462966
    Peer-reviewed2026-06-10

Cite this record

v1

Truvace Impact Record TRV-2026-2522, v1: “It’s not what you say, but how you say it: Using artifact intelligence to detect deception in natural speech in an HR recruiting context.” Truvace, 2026-11-12. /record/TRV-2026-2522 (accessed on the day you copy it). sha256 49dcb576d1a7ce9b…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv149dcb576d1a7…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2522 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.