Lying Through One’s Teeth: A Study on Verbal Leakage Cues

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4504–4510 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 4504 Lying Through One’s Teeth: A Study on Verbal Leakage Cues Min-Hsuan Yeh and Lun-Wei Ku Institute of Information Science, Acadimia Sinica Taipei, Taiwan {samuelyeh, lwku}@iis.sinica.edu.tw Abstract Although many studies use the LIWC lexicon to show the existence of verbal leakage cues in lie detection datasets, none mention how ver- bal 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 signifi- cance, 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 valid- ity 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 num- ber of strong cues—yield superior results, sug- gesting that verbal leakage cues are a key fac- tor for selecting lie detection datasets. 1 Introduction One theory of lie detection is about cues to lying: Why and when do liars and truth-tellers display different behavior? Ekman and Friesen (1969) pro- posed two categories of cues: deception cues and leakage cues. Deception cues relate to the content of lies, such as an inconsistency in one’s story; leakage cues appear because liars’ emotions betray their true feeling, which can be further classified into non-verbal and verbal leakage cues. Zuck- erman et al. (1981) reject the utility of focusing on liars’ emotions but link such cues to cognitive load, supported by Vrij et al. (2008, 2016, 2017). DePaulo et al. (2003) analyzes 158 cues to decep- tion, including non-verbal and verbal leakage cues, finding that verbal leakage cues are more reliable than others. Studies such as Adams (1996), Smith (2001), and Levitan (2019) show that verbal leak- age cues can be found through psycholinguistic dictionaries such as the LIWC lexicon (Pennebaker et al., 1999), LDI (Bachenko et al., 2008; Enos, 2009), and Harbingers (Niculae et al., 2015). Many NLP studies have recently collected lie detection datasets and detected lies using computa- tional models (Hirschberg et al., 2005; Pérez-Rosas et al., 2014; Peskov et al., 2020); most of these ig- nore traditional lie detection methods and findings, and have no follow-up studies, making it difficult to know which datasets are suitable for model training. To use machine learning approaches together with lie detection research in psychology and linguistics, and to seek a way to evaluate and select proper datasets, this study focuses on analyzing verbal leakage cues within; leakage cues hereafter indi- cate verbal leakage cues. We study leakage cues in terms of the data collection method and model per- formance. …

Content truncated to 500 words