Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies
Humans rarely perform better than chance at lie detection. To better understand human perception of deception, we created a game framework, LieCatcher, to collect ratings of perceived deception using a large corpus of deceptive and truthful interviews. We analyzed the acoustic-prosodic and linguisti...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
The MIT Press
2020-07-01
|
Series: | Transactions of the Association for Computational Linguistics |
Online Access: | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00311 |
_version_ | 1811264321327464448 |
---|---|
author | Chen, Xi (Leslie) Ita Levitan, Sarah Levine, Michelle Mandic, Marko Hirschberg, Julia |
author_facet | Chen, Xi (Leslie) Ita Levitan, Sarah Levine, Michelle Mandic, Marko Hirschberg, Julia |
author_sort | Chen, Xi (Leslie) |
collection | DOAJ |
description | Humans rarely perform better than chance at lie detection. To better understand human perception of deception, we created a game framework, LieCatcher, to collect ratings of perceived deception using a large corpus of deceptive and truthful interviews. We analyzed the acoustic-prosodic and linguistic characteristics of language trusted and mistrusted by raters and compared these to characteristics of actual truthful and deceptive language to understand how perception aligns with reality. With this data we built classifiers to automatically distinguish trusted from mistrusted speech, achieving an F1 of 66.1%. We next evaluated whether the strategies raters said they used to discriminate between truthful and deceptive responses were in fact useful. Our results show that, although several prosodic and lexical features were consistently perceived as trustworthy, they were not reliable cues. Also, the strategies that judges reported using in deception detection
were not helpful for the task. Our work sheds light on the nature of trusted language and provides insight into the challenging problem of human deception detection. |
first_indexed | 2024-04-12T20:00:58Z |
format | Article |
id | doaj.art-4f6fede2699a47019debf80967b52755 |
institution | Directory Open Access Journal |
issn | 2307-387X |
language | English |
last_indexed | 2024-04-12T20:00:58Z |
publishDate | 2020-07-01 |
publisher | The MIT Press |
record_format | Article |
series | Transactions of the Association for Computational Linguistics |
spelling | doaj.art-4f6fede2699a47019debf80967b527552022-12-22T03:18:31ZengThe MIT PressTransactions of the Association for Computational Linguistics2307-387X2020-07-01819921410.1162/tacl_a_00311Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect LiesChen, Xi (Leslie)Ita Levitan, SarahLevine, MichelleMandic, MarkoHirschberg, JuliaHumans rarely perform better than chance at lie detection. To better understand human perception of deception, we created a game framework, LieCatcher, to collect ratings of perceived deception using a large corpus of deceptive and truthful interviews. We analyzed the acoustic-prosodic and linguistic characteristics of language trusted and mistrusted by raters and compared these to characteristics of actual truthful and deceptive language to understand how perception aligns with reality. With this data we built classifiers to automatically distinguish trusted from mistrusted speech, achieving an F1 of 66.1%. We next evaluated whether the strategies raters said they used to discriminate between truthful and deceptive responses were in fact useful. Our results show that, although several prosodic and lexical features were consistently perceived as trustworthy, they were not reliable cues. Also, the strategies that judges reported using in deception detection were not helpful for the task. Our work sheds light on the nature of trusted language and provides insight into the challenging problem of human deception detection.https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00311 |
spellingShingle | Chen, Xi (Leslie) Ita Levitan, Sarah Levine, Michelle Mandic, Marko Hirschberg, Julia Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies Transactions of the Association for Computational Linguistics |
title | Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies |
title_full | Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies |
title_fullStr | Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies |
title_full_unstemmed | Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies |
title_short | Acoustic-Prosodic and Lexical Cues to Deception and Trust: Deciphering How People Detect Lies |
title_sort | acoustic prosodic and lexical cues to deception and trust deciphering how people detect lies |
url | https://www.mitpressjournals.org/doi/abs/10.1162/tacl_a_00311 |
work_keys_str_mv | AT chenxileslie acousticprosodicandlexicalcuestodeceptionandtrustdecipheringhowpeopledetectlies AT italevitansarah acousticprosodicandlexicalcuestodeceptionandtrustdecipheringhowpeopledetectlies AT levinemichelle acousticprosodicandlexicalcuestodeceptionandtrustdecipheringhowpeopledetectlies AT mandicmarko acousticprosodicandlexicalcuestodeceptionandtrustdecipheringhowpeopledetectlies AT hirschbergjulia acousticprosodicandlexicalcuestodeceptionandtrustdecipheringhowpeopledetectlies |