@inproceedings{yeh-ku-2021-lying,
title = "Lying Through One{'}s Teeth: A Study on Verbal Leakage Cues",
author = "Yeh, Min-Hsuan and
Ku, Lun-Wei",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.370",
doi = "10.18653/v1/2021.emnlp-main.370",
pages = "4504--4510",
abstract = "Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how verbal leakage cues are influenced by means of data collection, or the impact thereof on the performance of models. In this paper, we study verbal leakage cues to understand the effect of the data construction method on their significance, and examine the relationship between such cues and models{'} validity. The LIWC word-category dominance scores of seven lie detection datasets are used to show that audio statements and lie-based annotations indicate a greater number of strong verbal leakage cue categories. Moreover, we evaluate the validity of state-of-the-art lie detection models with cross- and in-dataset testing. Results show that in both types of testing, models trained on a dataset with more strong verbal leakage cue categories{---}as opposed to only a greater number of strong cues{---}yield superior results, suggesting that verbal leakage cues are a key factor for selecting lie detection datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yeh-ku-2021-lying">
<titleInfo>
<title>Lying Through One’s Teeth: A Study on Verbal Leakage Cues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Min-Hsuan</namePart>
<namePart type="family">Yeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how verbal leakage cues are influenced by means of data collection, or the impact thereof on the performance of models. In this paper, we study verbal leakage cues to understand the effect of the data construction method on their significance, and examine the relationship between such cues and models’ validity. The LIWC word-category dominance scores of seven lie detection datasets are used to show that audio statements and lie-based annotations indicate a greater number of strong verbal leakage cue categories. Moreover, we evaluate the validity of state-of-the-art lie detection models with cross- and in-dataset testing. Results show that in both types of testing, models trained on a dataset with more strong verbal leakage cue categories—as opposed to only a greater number of strong cues—yield superior results, suggesting that verbal leakage cues are a key factor for selecting lie detection datasets.</abstract>
<identifier type="citekey">yeh-ku-2021-lying</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.370</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.370</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4504</start>
<end>4510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lying Through One’s Teeth: A Study on Verbal Leakage Cues
%A Yeh, Min-Hsuan
%A Ku, Lun-Wei
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F yeh-ku-2021-lying
%X Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how verbal leakage cues are influenced by means of data collection, or the impact thereof on the performance of models. In this paper, we study verbal leakage cues to understand the effect of the data construction method on their significance, and examine the relationship between such cues and models’ validity. The LIWC word-category dominance scores of seven lie detection datasets are used to show that audio statements and lie-based annotations indicate a greater number of strong verbal leakage cue categories. Moreover, we evaluate the validity of state-of-the-art lie detection models with cross- and in-dataset testing. Results show that in both types of testing, models trained on a dataset with more strong verbal leakage cue categories—as opposed to only a greater number of strong cues—yield superior results, suggesting that verbal leakage cues are a key factor for selecting lie detection datasets.
%R 10.18653/v1/2021.emnlp-main.370
%U https://aclanthology.org/2021.emnlp-main.370
%U https://doi.org/10.18653/v1/2021.emnlp-main.370
%P 4504-4510
Markdown (Informal)
[Lying Through One’s Teeth: A Study on Verbal Leakage Cues](https://aclanthology.org/2021.emnlp-main.370) (Yeh & Ku, EMNLP 2021)
ACL
- Min-Hsuan Yeh and Lun-Wei Ku. 2021. Lying Through One’s Teeth: A Study on Verbal Leakage Cues. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4504–4510, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.