“Does it Matter When I Think You Are Lying?” Improving Deception Detection by Integrating Interlocutor’s Judgements in Conversations

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1846–1860 August 1–6, 2021. ©2021 Association for Computational Linguistics 1846 “Does it Matter When I Think You Are Lying?” Improving Deception Detection by Integrating Interlocutor’s Judgements in Conversations Huang-Cheng Chou1,3, Woan-Shiuan Chien1,3, Da-Cheng Juan2, Chi-Chun Lee1,3 1Department of Electrical Engineering, National Tsing Hua University, Taiwan 2Department of Computer Science, National Tsing Hua University, Taiwan 3MOST Joint Research Center for AI Technology and All Vista Healthcare, Taiwan {hc.chou,wschien,dacheng}@gapp.nthu.edu.tw, cclee@ee.nthu.edu.tw Abstract It is well known that human is not good at de- ception detection because of a natural inclina- tion of truth-bias. However, during a conversa- tion, when an interlocutor (interrogator) is be- ing asked explicitly to assess whether his/her interacting partner (deceiver) is lying, this per- ceptual judgment depends highly on how the interrogator interprets the context of the con- versation. While the deceptive behaviors can be difficult to model due to their heteroge- neous manifestation, we hypothesize that this contextual information, i.e., whether the inter- locutor trusts or distrusts what his/her partner is saying, provides an important condition in which the deceiver’s deceptive behaviors are more consistently distinct. In this work, we propose a Judgmental-Enhanced Automatic Deception Detection Network (JEADDN) that explicitly considers interrogator’s perceived truths-deceptions with three types of speech- language features (acoustic-prosodic, linguis- tic, and conversational temporal dynamics fea- tures) extracted during a conversation. We evaluate our framework on a large Mandarin Chinese Deception Dialog Database. The re- sults show that the method significantly out- performs the current state-of-the-art approach without conditioning on the judgements of interrogators on this database. We further demonstrate that the behaviors of interrogators are important in detecting deception when the interrogators distrust the deceivers. Finally, with the late fusion of audio, text, and turn- taking dynamics (TTD) features, we obtain promising results of 87.27% and 94.18% accu- racy under the conditions that the interrogators trust and distrust the deceivers in deception detection which improves 7.27% and 13.57% than the model without considering the judge- ments of interlocutor respectively. 1 Introduction Deception behaviors frequently appear in human daily life, such as politics (Clementson, 2018), news (Conroy et al., 2015a; Vaccari and Chadwick, 2020), and business (Grazioli and Jarvenpaa, 2003; Triandis et al., 2001). Despite its frequent occur- rences, researchers have repeatedly shown that hu- mans are not good at detecting deceptions (it’s 54% accuracy on average for both police officers and college students (Vrij and Graham, 1997)), even for highly-skilled professionals, such as teachers, social workers, and police officers (Hartwig et al., 2004; Vrij et al., 2006). Due to the difficulty in identifying deceptions by human, researchers have also developed an automatic deception detection (ADD) systems applied in various fields, such as cybercrime (Mbaziira and Jones, 2016), fake news detection (Conroy et al., 2015b), employment inter- views (Levitan et al., 2018b,a), and even court deci- sion (Venkatesh et al., 2019; P´erez-Rosas, Ver´onica and Abouelenien, Mohamed and Mihalcea, Rada and Burzo, Mihai, 2015). Although many works have studied approaches of automatic deception de- tection, few …

Content truncated to 500 words