Honesty Repeats Itself: Comparing Manual and Automated Coding on the Veracity Cues Total Details and Redundancy

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989592%3A15210%2F24%3A73625443" target="_blank" >RIV/61989592:15210/24:73625443 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.cambridge.org/core/journals/applied-psycholinguistics/article/honesty-repeats-itself-comparing-manual-and-automated-coding-on-the-veracity-cues-total-details-and-redundancy/02C3596C4B0A4A6D9845D711A99141B2" target="_blank" >https://www.cambridge.org/core/journals/applied-psycholinguistics/article/honesty-repeats-itself-comparing-manual-and-automated-coding-on-the-veracity-cues-total-details-and-redundancy/02C3596C4B0A4A6D9845D711A99141B2</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.17029/73bf0f42-b599-4c36-81b7-0c87befb795f" target="_blank" >10.17029/73bf0f42-b599-4c36-81b7-0c87befb795f</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Honesty Repeats Itself: Comparing Manual and Automated Coding on the Veracity Cues Total Details and Redundancy

Popis výsledku v původním jazyce

Lie detection research comparing manual and automated coding of linguistic cues is limited.In Experiment 1, we attempted to extend this line of research by directly comparing theveracity differences in manual coding and two coding software programs (Text Inspector andLIWC) on the linguistic cue ‘total details’ across eight published datasets. Mixed modelanalyses revealed that LIWC showed larger veracity differences in total details than TextInspector and Manual coding. Follow-up classification analyses showed that both automatedcoding and manual coding could accurately classify honest and false accounts. In Experiment2, we examined if LIWC’s sensitivity to veracity differences was the result of honestaccounts including more redundant (repeated) words than false accounts as LIWC—but notText Inspector or Manual coding—accounts for redundancy. Our prediction was supportedand the most redundant words were function words. The results implicated that automatedcoding can detect veracity differences in total details and redundancy but it is not necessarilybetter than manual coding at accurately classifying honest and false accounts.

Název v anglickém jazyce

Honesty Repeats Itself: Comparing Manual and Automated Coding on the Veracity Cues Total Details and Redundancy

Popis výsledku anglicky

Lie detection research comparing manual and automated coding of linguistic cues is limited.In Experiment 1, we attempted to extend this line of research by directly comparing theveracity differences in manual coding and two coding software programs (Text Inspector andLIWC) on the linguistic cue ‘total details’ across eight published datasets. Mixed modelanalyses revealed that LIWC showed larger veracity differences in total details than TextInspector and Manual coding. Follow-up classification analyses showed that both automatedcoding and manual coding could accurately classify honest and false accounts. In Experiment2, we examined if LIWC’s sensitivity to veracity differences was the result of honestaccounts including more redundant (repeated) words than false accounts as LIWC—but notText Inspector or Manual coding—accounts for redundancy. Our prediction was supportedand the most redundant words were function words. The results implicated that automatedcoding can detect veracity differences in total details and redundancy but it is not necessarilybetter than manual coding at accurately classifying honest and false accounts.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50101 - Psychology (including human - machine relations)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

APPLIED PSYCHOLINGUISTICS

ISSN

0142-7164

e-ISSN

1469-1817

Svazek periodika

2024

Číslo periodika v rámci svazku

Online first

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

29

Strana od-do

1-29

Kód UT WoS článku

001337070700001

EID výsledku v databázi Scopus

2-s2.0-85207357218