=Paper=
{{Paper
|id=Vol-3900/Paper16
|storemode=property
|title=Deep Learning-Enhanced Detection of Lie Tendencies through Answer Pattern Analysis
|pdfUrl=https://ceur-ws.org/Vol-3900/Paper16.pdf
|volume=Vol-3900
|authors=Debanil Chanda,Rakesh Kumar Mandal
|dblpUrl=https://dblp.org/rec/conf/dosier/ChandaM24
}}
==Deep Learning-Enhanced Detection of Lie Tendencies through Answer Pattern Analysis==
https://ceur-ws.org/Vol-3900/Paper16.pdf
Deep Learning-Enhanced Detection of Lie Tendencies
through Answer Pattern Analysis
Debanil Chanda1,*,† , Rakesh Kumar Mandal1,†
1
Department of Computer Science & Technology, University of North Bengal), Raja Rammohanpur, Darjeeling, West Bengal
734013, India
Abstract
Detecting deceptive behavior is a critical challenge across various domains, including security, recruitment,
and criminal investigations. Traditional methods, such as polygraphs, rely on physiological cues and often lack
reliability and scalability. This study introduces a deep learning-based methodology that enhances deception
detection through the analysis of answer patterns derived from a Strategic Interview Technique (SIT) and publicly
available datasets, including LIAR and Deceptive Opinion Spam. By integrating cognitive behavioral features
such as response consistency, delay, and reactions to unexpected questions with textual embeddings generated
from Bi-LSTM networks, the model provides a comprehensive framework for detecting lie tendencies. The
proposed method demonstrates exceptional performance, achieving an accuracy of 89.5% and an F1-score of 88.9%,
outperforming recent studies in the field. Comparative analysis highlights its robustness in distinguishing truthful
and deceptive responses across structured and unstructured data. Error analysis reveals areas for refinement,
including addressing false positives caused by ambiguous responses and false negatives in rehearsed deception.
The model’s reliance on cost-effective and non-invasive features makes it scalable and practical for real-world
applications. This work lays the foundation for integrating multimodal data, such as audio and video, to further
enhance the effectiveness of deception detection systems.
Keywords
Lie detection, Deep Learning, Answer Pattern Analysis, Strategic Interview Technique (SIT), Behavioral Analysis
1. Introduction
1.1. Significance
Lie detection is a critical area of research with applications in law enforcement, recruitment, and
psychological assessments. Traditional methods, such as polygraphs, rely on physiological signals but
face criticism for being invasive and susceptible to countermeasures and prone to manipulation [1, 2].
Advances in behavioral and linguistic analysis offer a more robust alternative [3]. Answer patterns
during structured interviews, for instance, provide cognitive and behavioral cues that are valuable
for detecting deception [4, 5]. Some lie detection techniques rely on question-answering approaches,
such as the Pattern Variation Method to Detect Lie using Artificial Neural Network (PVMANN) and
the Pattern Variation Method with Modified Weights to Detect Lie using Artificial Neural Network
(PVMMWANN) [6, 7]. Both methods only require a personal computer, with suspects interviewed in a
tension-free environment. In these methods, the same questions are asked daily over several days. It
was believed that longer intervals between interviews might lead to inconsistencies in a liar’s answers,
as repeated interrogation could exploit cognitive strain [8]. However, studies have shown that liars can
be as consistent as truthful individuals, even with extended intervals between interviews. This creates
challenges for traditional repetitive questioning approaches, as liars may rehearse their answers to
appear truthful [9]. To address this, interviews should be conducted strategically, where repeating the
same answer becomes difficult for the suspect. Strategically framed questions make it easier to detect
deception without relying on visible negative signs. Such techniques enable the distinction between
The 2024 Sixth Doctoral Symposium on Intelligence Enabled Research (DoSIER 2024), November 28-29, 2024, Jalpaiguri, India
*
Corresponding author.
†
These authors contributed equally.
$ dchanda6@gmail.com (D. Chanda); rakeshmandal@nbu.ac.in (R. K. Mandal)
0000-0002-8183-1759 (D. Chanda); 0000-0002-0471-6925 (R. K. Mandal)
© 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
truthful and dishonest individuals by introducing subtle variations in the questioning process, forcing
liars to engage cognitively in ways that reveal inconsistencies [10, 11].
1.2. Related Work
Lie detection has been an essential focus of study, with traditional methods such as polygraph testing
relying on physiological signals like heart rate, skin conductance, and respiratory patterns [12, 13].
While widely used, these methods have several limitations, including invasiveness, high dependency
on instrumentation, and susceptibility to countermeasures [1]. These drawbacks have motivated
researchers to explore alternative approaches that focus on cognitive and behavioral indicators [5].
Several techniques based on question-answering have been developed to detect deception. Notable
among these are the Pattern Variation Method to Detect Lie using Artificial Neural Network (PVMANN)
and the Pattern Variation Method with Modified Weights to Detect Lie using Artificial Neural Network
(PVMMWANN) [6, 7]. Both methods are efficient, requiring only a personal computer, and involve
interviewing individuals in a relaxed, tension-free environment. The same questions are repeated daily
over several days to detect inconsistencies, under the assumption that liars would struggle to maintain
consistency over time. However, research has shown that liars can exhibit consistency levels comparable
to truthful individuals, even with extended intervals between interviews [9]. These findings suggest
that repetitive questioning alone may not be sufficient to detect deception, especially for well-prepared
individuals [14]. To address this limitation, strategically designed questions have been proposed,
making it difficult for liars to maintain fabricated answers while remaining straightforward for truthful
individuals [15]. This approach leverages cognitive load and behavioral variability to improve the
accuracy of deception detection [8, 16]. Some studies have explored unconventional tools for deception
detection, such as analyzing cognitive tasks like drawing to reveal inconsistencies in liar individuals
[17]. Dialog-based systems have also been explored for deception detection, leveraging natural language
processing to identify linguistic cues [18]. Machine learning techniques have also been extensively
explored in this domain, particularly for analyzing textual and behavioral data [19]. Early machine
learning models, such as support vector machines and decision trees, relied heavily on handcrafted
features like n-grams and sentiment analysis to classify responses as truthful or deceptive [20, 21, 22].
Although these methods demonstrated potential, their scalability and performance were limited when
applied to large or unstructured datasets [20, 21]. Deep learning progress has greatly enhanced the
field by enabling the analysis of complex patterns in multimodal data. Methods like the hybrid CNN-
LSTM architecture proposed by Mendels et al. (2017), the multimodal neural network developed by
Krishnamurthy et al. (2018) and the language-guided deep learning model explored by Wang et al
(2020) achieved promising results by integrating audio, text, and visual features [19, 22]. While effective,
these approaches often require multimodal datasets and computational resources, making them less
practical for general use. Existing methods often face challenges related to scalability, data requirements,
and generalizability [2]. By leveraging behavioral metrics and deep learning techniques, the proposed
approach addresses these limitations, contributing to the advancement of lie detection research.
1.3. Objective
This research aims to develop a robust deep learning-based framework for detecting deception by
integrating textual and behavioral features. The key objectives of this study are:
• Incorporating Behavioral Metrics: Utilize response consistency, delay, and unexpected ques-
tion reactions derived from SIT to detect cognitive strain indicative of deception [23, 24].
• Leveraging Deep Learning: Design a Bi-LSTM-based architecture to process both behavioral
and textual features, enhancing detection accuracy [25, 26].
• Evaluating Model Performance: Compare the proposed methodology with existing approaches
using accuracy, precision, recall, and F1-score as metrics [3, 19, 20].
• Real-World Applicability: Demonstrate the practicality of the methodology for applications
such as recruitment, security assessments, and criminal investigations [27].
Table 1
Sample Strategic Interview Questions and Expected Response Patterns
Question No Category Sample Question Type
1 Personal Detail Are you currently employed? Yes/No
2 Personal Detail Do you work for a private company? Yes/No
3 Finances Do you have any outstanding loans? Yes/No
4 Finances Are all your debts paid off? Yes/No
5 Qualifications Do you hold a graduate degree? Yes/No
6 Qualifications Did you complete any certifications? Yes/No
7 Lifestyle Do you exercise regularly Yes/No
8 Lifestyle Have you been active this past week? Yes/No
By achieving these objectives, this work bridges the gap between traditional behavioral analysis and
modern deep learning techniques, providing a scalable, efficient, and effective solution for deception
detection.
2. Methodology
This study employs a deep learning-based approach to detect lie by integrating textual and behavioural
features derived from multiple datasets. The methodology includes data collection, feature engineering
and the design of hybrid Bi-LSTM model that leverages the complementary strength of behavioural
and linguistic analysis.
2.1. Data Collection and Preparation
The model is trained and evaluated on a combined dataset consisting of three sources. The LIAR dataset
[22], the Deceptive Opinion Spam dataset [20] and a custom Strategic Interview Technique (SIT)
dataset.
2.1.1. Strategic Interview Technique (SIT) Dataset
SIT involves strategically farmed and repeated questions to elicit consistent or deceptive behavioral
patterns, where interviewees are subtly challenged to maintain consistency. Table 1 shows sample
interview questions, demonstrating both the repetitive nature and variations in phrasing used to
encourage cognitive consistency. The variety of topics and rephrasing within each category are aimed at
detecting changes in response consistency [28]. Collected responses include- Yes/No answers, Response
time and Cognitive matrix, Reaction to unexpected or cognitively challenging questions.
2.1.2. LIAR Dataset
• Includes 12,836 labelled political statements with metadata (e.g., speaker, context, credibility).
• Truthfulness levels: true, mostly true, half true, false, barely true and pants on fire.
2.1.3. Deceptive Opinion Dataset
• Provides 1600 truthful and deceptive hotel reviews, categorized into positive and negative state-
ments.
• Features: Textual content, word count and sentiment polarity.
The datasets were combined, as shown in Table 2, to train the model effectively. The combination of
these datasets provides several advantages, enhancing the robustness and generalizability of the study.
The benefits are-
Table 2
Combined Dataset for Training
ID Source Textual Content Consistency Score (C) Response Delay (R) Unexpected Question Score (UQS) Truthfulness Label
001 SIT “Yes” 0.25 1.5 0.35 Truthful
002 LIAR “The economy grew 5% last year” N/A N/A N/A Barely True
003 Deceptive Opinion Spam “The hotel was amazing” N/A N/A N/A Deceptive
004 SIT “No” 0.65 3.0 0.70 Deceptive
005 LIAR “We reduced taxes by 20% in 2020” N/A N/A N/A Mostly True
006 Deceptive Opinion Spam “Terrible experience, won’t stay again” N/A N/A N/A Truthful
007 SIT “Yes” 0.40 2.2 0.55 Truthful
008 LIAR “Crime rates are lower now than ever.” N/A N/A N/A False
009 Deceptive Opinion Spam “Best place I’ve ever visited!” N/A N/A N/A Deceptive
010 SIT “No” 0.50 2.8 0.60 Truthful
• The model is trained and tested across diverse domains including structured interviews, polit-
ical discourse and consumer opinions. This improves the model’s adaptability to real-world
applications.
• The combined datasets expose the model to a wide variety of features, enabling it to detect
deception in different scenarios.
• Combination of these datasets facilitates a detailed error analysis to identify domain-specific
challenges.
• The integration ensures the model learns from both structured features (e.g., response consistency)
and unstructured text data (e.g., liar statements, consumer reviews).
2.2. Feature Engineering and Preprocessing
The success of any deep learning-based deception detection system relies heavily on the quality of
features extracted from the input data. This study integrates three distinct datasets—responses collected
via the Strategic Interview Technique (SIT), the LIAR dataset, and the Deceptive Opinion Spam dataset.
Each dataset undergoes tailored preprocessing and feature engineering to ensure consistency and
compatibility for training a unified deep learning model.
2.2.1. Behavioral Features (SIT)
• Response Consistency (C): The calculation of the Response Consistency is shown in Equation
1: ∑︀𝑛
(𝑥𝑖 − 𝑥¯)2
𝐶 = 𝑖=1 (1)
𝑛
Where, 𝑛 is the number of repeated responses, 𝑥𝑖 is the response at instance 𝑖, 𝑥
¯ is the mean
response. A higher 𝐶 may indicate potential deception.
• Response Delay (R): The formula to calculate the Response Delay is shown in the Equation 2:
∑︀𝑛
𝑡𝑖
𝑅 = 𝑖=1 (2)
𝑛
Where 𝑡𝑖 is the time taken for each response. Increased 𝑅 suggests cognitive processing, often
associated with deception.
• Unexpected Question Score (UQS): An Unexpected Question Score (UQS) is calculated by
averaging response variances to unexpected questions. Higher UQS values indicate spontaneous
inconsistencies, a potential indicator of deception.
2.2.2. Textual Features (LIAR and Deceptive Opinion Spam Datasets)
Both the LIAR and Deceptive Opinion Spam datasets provide textual data labeled as truthful or deceptive.
The following preprocessing steps are applied to ensure the extraction of meaningful semantic and
syntactic features:
• Text Cleaning:
– Removal of punctuation, special characters, and stopwords.
– Conversion to lowercase to standardize input.
• Tokenization and Lemmatization:
– Tokenization splits sentences into individual words.
– Lemmatization reduces words to their base or dictionary forms, ensuring consistency.
• Word Embedding:
– Represent words as dense vectors using pretrained embeddings such as BERT. These em-
beddings capture semantic and syntactic relationships between words [29].
– BERT embeddings are particularly beneficial as they consider the context of words in a
sentence, providing a nuanced representation of deceptive statements.
2.2.3. Sentiment and Metadata Features
• Sentiment Analysis: Sentiment polarity scores (positive, negative, or neutral) are extracted
using natural language processing (NLP) libraries like VADER [30]. These scores are particularly
relevant for the Deceptive Opinion Spam dataset, as deceptive reviews often exhibit exaggerated
sentiment.
• Metadata Encoding: Speaker credibility, political affiliation, and context from the LIAR dataset
are encoded numerically using one-hot encoding or embedding layers, depending on the deep
learning model’s architecture.
2.2.4. Data Normalization and Augmentation
To ensure uniformity and enhance model generalizability, the following techniques are used:
• Normalization: Numerical features (e.g., C, R, UQS) are normalized using Min-Max scaling [31],
as shown in the Equation 3:
𝑥 − min(𝑥)
𝑥′ = (3)
max(𝑥) − min(𝑥)
Where, 𝑥 represents the original feature value, min(𝑥) and max(𝑥) are minimum and maximum
values of the feature in the dataset and 𝑥′ is the normalized value.
• Data Augmentation: Synthetic samples are generated for the SIT dataset by simulating varia-
tions in response delay and consistency, ensuring balance between truthful and deceptive classes.
Textual data augmentation includes synonym replacement and backtranslation techniques, par-
ticularly for small subsets of the Deceptive Opinion Spam dataset.
2.3. Deep Learning Model Architecture
The deep learning framework developed in this study is designed to analyze both textual and behavioral
features, leveraging their complementary nature to detect deceptive tendencies with high accuracy. The
model employs a multi-branch architecture that processes distinct feature types—textual embeddings and
behavioral metrics—through specialized neural network layers, culminating in a unified classification
output.
2.3.1. Overview of the Architecture
• A textual branch that processes semantic information using a Bi-directional Long Short-Term
Memory (Bi-LSTM) network.
• A behavioral branch that analyzes numerical features using fully connected dense layers.
These branches are integrated through a concatenation layer, followed by a classification layer that
predicts the likelihood of truthfulness or deception. The modular nature of this architecture allows
seamless incorporation of additional feature types, such as metadata or audio signals, if required.
2.3.2. Input Layers
The input to the model consists of:
• Textual Data: Preprocessed text embeddings from the LIAR and Deceptive Opinion Spam
datasets. Embeddings are generated using pretrained BERT models, capturing both semantic and
contextual nuances.
• Textual Data: Numerical features derived from SIT responses, including: Response Consistency
(C), Response Delay (R), Unexpected Question Reaction (UQS).
Each input type is normalized and scaled to ensure compatibility with the subsequent layers.
2.3.3. Textual Feature Processing (Bi-LSTM)
The textual branch employs a Bi-LSTM network to capture sequential dependencies and contextual
relationships in the input text:
• Embedding Layer: Pretrained BERT embeddings are used to represent each word as a dense
vector. These embeddings are fine-tuned during training to align with the deception detection
task.
• Bi-LSTM Layer: The Bi-LSTM network processes the sequence of embeddings, capturing
both forward and backward temporal dependencies. The hidden states of the Bi-LSTM encode
contextual relationships between words, which are crucial for detecting nuanced patterns of
deception.
• Dropout Layer: A dropout rate of 0.3 is applied to prevent overfitting, ensuring robust general-
ization to unseen data.
The output of the Bi-LSTM layer is a fixed-dimensional vector representing the entire input text, which
is passed to the concatenation layer.
2.3.4. Behavioral Feature Processing (Dense Layers)
The behavioral branch processes numerical features through fully connected dense layers:
• Input Layer: Accepts normalized behavioral features (C, R, and UQS) as input.
• Dense Layers: Two fully connected layers, each with 128 and 64 neurons, apply non-linear
transformations using ReLU activation. These layers enable the network to learn complex
relationships among behavioral metrics.
• Dropout Layer: A dropout rate of 0.2 is applied after each dense layer to reduce overfitting.
The final output of the behavioral branch is a feature vector summarizing patterns in the behavioral
data.
2.3.5. Integration (Concatenation Layer)
The outputs of the Bi-LSTM and dense layers are concatenated into a unified feature vector. This layer
enables the model to jointly analyze textual and behavioral patterns, leveraging their complementary
strengths.
2.3.6. Classification Layer
The concatenated feature vector is passed through a series of dense layers for classification:
• Dense Layers: Two fully connected layers with 64 and 32 neurons, using ReLU activation.
• Output Layer: A softmax layer outputs probabilities for two classes: truthful and liar.
The final prediction is based on the class with the highest probability.
Figure 1: Block diagram of the proposed deep learning-based methodology for detecting deceptive behavior.
2.3.7. Loss Function and Optimization
The model is trained to minimize the Categorical Cross-Entropy Loss, shown in Equation 4:
𝑁 𝐾
1 ∑︁ ∑︁
𝐿=− 𝑦𝑖𝑗 log(ˆ
𝑦𝑖𝑗 ) (4)
𝑁
𝑖=1 𝑗=1
Where 𝑦𝑖𝑗 is the true label for class 𝑗 of sample 𝑖, 𝑦ˆ𝑖𝑗 is the predicted probability for class 𝑗, 𝑁 is the
number of samples, and 𝐾 is the number of classes (truthful and liar). The textbfAdam optimizer is used
for efficient and adaptive gradient updates, with an initial learning rate of 10−4 [32]. Early stopping is
applied during training to prevent overfitting [33].
2.3.8. Model Training and Validation
The combined dataset was divided into training (80%), validation (10%) and test (10%) sets. Cross
validation was employed to ensure generalizability across diverse data domains. Training Set is Used
to update the model weights., Validation Set Monitors during training for early stopping and Test
Set Evaluates the model’s generalization performance on unseen data. A batch size of 32 is used, with
training conducted over 50 epochs or until early stopping criteria are met. Performance is measured
using accuracy, precision, recall, and F1 score. The overall workflow is illustrated in Figure 1, which
provides a step-by-step depiction of how the inputs are processed, features are extracted, and predictions
are made.
3. Result Analysis and Discussion
The proposed methodology integrates cognitive principles with deep learning models to effectively
classify truthful and deceptive responses. The evaluation is based on behavioral features from SIT and
textual patterns from LIAR and Deceptive Opinion Spam datasets. The model’s performance is analyzed
using key metrics, comparative studies, and visual aids, ensuring a comprehensive understanding of its
capabilities.
Table 3
Performance Metric of the Proposed Model
Metric Value
Accuracy 89.5
Precision 85.7
Recall 92.4
F1-Score 88.9
Figure 2: Performance Metrics of the Proposed Model.
Table 4
Comparison with Recent Works
Method Dataset Model Accuracy (%) Precision (%) Recall (%) F1-Score (%)
Mendels et al. (2017) Proprietary Dataset (Audio + Text) Hybrid Deep Learning (CNN + LSTM) 86.2 83.5 90.0 86.6
Krishnamurthy et al. (2018) Real-Life Videos (Multimodal) Multimodal Neural Model 88.1 84.2 91.0 87.5
Wang et al. (2020) Custom Deception Dataset Language-Guided Deep Learning 88.5 88.2 87.0 86.8
Proposed Model SIT + LIAR + Deceptive Opinion Spam Bi-LSTM + Dense Layers 89.5 85.7 92.4 88.9
3.1. Model Performance
The performance of the proposed model was evaluated using standard metrics: accuracy, precision,
recall, and F1-score. The results are presented in Figure 2 and Table 3. The proposed model achieves
high accuracy (89.5%) and recall (92.4%), outperforming traditional techniques. Its superior F1-score
(88.9%) highlights its balanced capability in identifying deceptive behavior while minimizing false
positives and negatives.
3.2. Comparison with Recent Works
The model’s performance is compared with other state-of-the-art methods, as shown in Table 4 and
visualized in Figure 3. The proposed methodology achieves the highest accuracy and recall among
the compared models. The integration of SIT behavioral features with textual embeddings gives it a
competitive advantage.
3.3. ROC Curve Analysis
The model’s discriminative capability is illustrated in Figure 4, which depicts the Receiver Operating
Characteristic (ROC) curve. The Area Under the Curve (AUC) value of 0.75 confirms the model’s
ability to reliably differentiate between truthful and deceptive responses.
Figure 3: Performance Comparison with Recent Works.
Figure 4: ROC Curve for the Proposed Model.
3.4. Error Analysis
A detailed error analysis was conducted shown in Figure 5 to identify limitations:
• False Positives: Truthful responses misclassified as deceptive, often due to ambiguous or overly
concise answers.
• False Negatives: Deceptive responses misclassified as truthful, typically observed in rehearsed
or highly consistent responses.
To mitigate these errors:
• Enhanced SIT Questions: Increase the variability and complexity of questions to induce greater
cognitive load.
• Augmented Training Data: Include more diverse examples of liar and truthful responses to
reduce bias.
Figure 5: Error Distribution for the Proposed Model.
Table 5
Comparison with Traditional Methods
Method Accuracy (%) Avg. Test Duration Instrumentation Requirement
Polygraph Test 72.0 1.5 – 4 hours Specialized equipment
PVMANN 78.5 45 minutes PC
PVMMWANN 82.3 40 minutes PC
Proposed Method 89.5 30 minutes PC
3.5. Comparison with Traditional Methods
As shown in the Table 5, the proposed model achieves significantly higher accuracy than traditional
techniques, such as the Polygraph Test, while requiring less time and no specialized equipment.
3.6. Discussion
The proposed methodology demonstrates significant advancements in deception detection by integrating
behavioral features from the Strategic Interview Technique (SIT) with textual data from the LIAR and
Deceptive Opinion Spam datasets. By leveraging deep learning architectures such as Bi-LSTM and
dense layers, the model achieves robust performance, with an accuracy of 89.5%, precision of 85.7%,
recall of 92.4%, and an F1-score of 88.9%. These metrics highlight the model’s ability to effectively
distinguish between truthful and deceptive responses across diverse datasets. A key strength of the
methodology lies in its integration of cognitive and textual features, which provides a comprehensive
analysis of deceptive behavior. Behavioral metrics such as consistency score, response delay, and
unexpected question score add valuable insights into cognitive patterns that are difficult to capture
using textual data alone. The inclusion of textual embeddings ensures that the model generalizes well
across unstructured data, making it versatile for a range of applications. Compared to recent works,
the proposed model outperforms methods such as the hybrid deep learning approach by Mendels et
al. (2017), the multimodal neural model by Krishnamurthy et al. (2018) and a language guided deep
learning method by Wang et al. (2020). These improvements are attributed to the innovative use of
SIT-derived behavioral metrics and the effective design of the deep learning architecture. Challenges
remain in addressing false positives caused by ambiguous truthful responses and false negatives in
rehearsed deceptive responses. Refining SIT question design to increase variability and cognitive load,
along with diversifying training datasets to include a broader demographic range, could further enhance
model performance. Despite these challenges, the methodology’s reliance on simple inputs and short
test durations makes it cost-effective, scalable, and practical for real-world applications. This work
establishes a strong foundation for future research. The integration of additional modalities, such as
audio or video, could further improve the detection of deception and expand the applicability of this
approach in domains such as security, recruitment, and criminal investigations.
4. Conclusion
In this study, an innovative approach was introduced for detecting an individual’ tendency to lie by
examining response patterns using an Artificial Neural Network (ANN) based on a Strategic Interview
Technique (SIT). Unlike traditional lie detection methods that rely heavily on physiological responses
or simplistic question-answering techniques, the proposed method analyzes subtle variations in answer
consistency and response delay. The findings reveal that the ANN-based SIT model achieves a high
accuracy rate of 89.5%, surpassing traditional methods such as Polygraph and previous ANN-based lie
detection techniques like PVMANN and PVMMWANN. By reducing the dependency on specialized
equipment and minimizing testing time, this model provides a practical and accessible alternative for
lie detection, particularly in settings where traditional methods may not be feasible or affordable. The
analysis of Consistency Score (CS) and Response Delay (RD) proved valuable in distinguishing between
truthful and deceptive individuals. While truthful individuals typically exhibit stable patterns and
shorter response times, deceptive individuals tend to show higher variability and delay, highlighting
cognitive load differences. However, certain limitations, such as the potential for manipulation by
highly trained individuals and emotional influence, suggest areas for future improvement. Integrating
additional biometrics, enhancing cultural sensitivity in questioning, and exploring adaptive question
models could further enhance accuracy and applicability. In conclusion, the proposed ANN-based SIT
model demonstrates significant progress in the field of lie detection by combining cognitive science
principles with machine learning techniques. The results underscore its potential for practical use
in criminal investigations, security assessments, and personnel evaluations, contributing a reliable,
cost-effective, and less intrusive alternative to traditional methods.
Acknowledgments
We sincerely thank the Civic Volunteers of Siliguri Metropolitan Police for their enthusiastic participation
in the interview sessions, which were crucial to this study. We are especially grateful to Mr. Sunil Yadav,
IPS, Assistant Commissioner Police (Traffic), for his invaluable support and for facilitating this research.
We also extend our gratitude to the academic community of the University of North Bengal—students,
scholars, and faculty members—for their cooperation, guidance, and valuable feedback, which greatly
enriched the quality of our work.
Declaration on Generative AI
During the preparation of this work, the author(s) used OpenAI’s ChatGPT to assist with grammar and
spelling checks. After using this tool, the author(s) reviewed and edited the content as needed and take
full responsibility for the publication’s content.
References
[1] Lykken, D. T. (1998). A Tremor in the Blood: Uses and Abuses of the Lie Detector. Springer.
[2] J. Charles F. Bond and B. M. DePaulo, "Accuracy of Deception Judgments," Personality and Social
Psychology Review, vol. 10, pp. 214-234, 2006, DOI: 10.1207/s15327957pspr1003_2.
[3] Wang, X., Peng, H., & Pan, S. (2020). Language-Guided Deep Learning for Deception
Detection. IEEE Transactions on Knowledge and Data Engineering, 32(4), 667–677, DOI:
10.1109/TKDE.2019.2892408.
[4] Zuckerman, M., DePaulo, B. M., & Rosenthal, R. (1981). Verbal and Nonverbal Communication of De-
ception. Advances in Experimental Social Psychology, 14, 1-59. DOI: 10.1016/S0065-2601(08)60369-
7.
[5] Vrij, A. (2008). Detecting Lies and Deceit: Pitfalls and Opportunities. John Wiley & Sons, ISBN:
978-0470516256.
[6] Chakraborty, S., & Mandal, R. K. (2016). Pattern Variation Method to Detect Lie Using Artificial
Neural Network (PVMANN). National Conference on Computational Technologies, 57-60.
[7] Mandal, R. K. (2016). Pattern Variation Method with Modified Weights to Detect Lie using Arti-
ficial Neural Network (PVMMWANN). AMSE JOURNALS, Modelling C, 77, 41-52, available at:
https://iieta.org/sites/default/files/Journals/MMC/MMC_C/2016.77.1_04.pdf.
[8] Vrij, A., Fisher, R. P., & Blank, H. (2017). A cognitive approach to lie detection: A meta-analysis.
Legal and Criminological Psychology, 22(1), 1–21, DOI: 10.1111/lcrp.12088.
[9] Granhag, P. A., & Stromwall, L. A. (2001). Deception detection based on repeated interrogations.
Legal and Criminological Psychology, 6, 85-101. DOI: 10.1348/135532501168217.
[10] Hartwig, M., Granhag, P. A., & Strömwall, L. A. (2007). Strategic use of evidence during police
interviews: When training to detect deception works. Law and Human Behavior, 31(2), 233–247,
DOI: 10.1007/s10979-006-9053-9.
[11] M. J, B.-G. I, M. C, H. C and I. I, "Strategic Interviewing to Detect Deception: Cues to Deception
across Repeated Interviews," Front. Psychol, vol. 7, pp. 1-17, 2016, DOI: 10.3389/fpsyg.2016.01702.
[12] National Research Council 2003, The Polygraph and Lie Detection, Washington, DC: The National
Academies Press, 2003, DOI: 10.17226/10420.
[13] A. Slavkovic, "Evaluating Polygraph Data," 2018, DOI: 10.1184/R1/6586598.v1.
[14] Vrij, A., Mann, S., & Fisher, R. P. (2006). Information-gathering vs. accusatory interview style:
Its impact on deception detection. Legal and Criminological Psychology, 11(1), 1–15, DOI:
10.1348/135532505X39099.
[15] Hartwig, M., Granhag, P. A., & Strömwall, L. A. (2007). Strategic use of evidence during police
interviews: When training to detect deception works. Law and Human Behavior, 31(2), 233–247,
DOI: 10.1007/s10979-006-9053-9.
[16] Walsh, D., & Bull, R. (2012). How do interviewers attempt to overcome suspects’ denials? Criminal
Behaviour and Mental Health, 22(2), 102–116, DOI: 10.1002/cbm.1829.
[17] Vrij, A., Leal, S., Fisher, R. P., Warmelink, L.,& Mann, S. (2018). Drawings as an innovative and
effective lie detection tool. Journal of Applied Psychology, 103(5), 501-513. DOI: 10.1037/apl0000298.
[18] Y. Tsunomori, G. Neubig, S. Sakti, T. Toda and S. Nakamura, "An Analysis Towards Dialogue-Based
Deception Detection," in Natural Language Dialog Systems and Intelligent Assistants, Springer,
ChamSpringer, Cham, 2015, pp. 177-187, DOI: 10.1007/978-3-319-19291-8_17.
[19] Krishnamurthy, S., Ramesh, S., & Elhabian, S. (2018). "Multimodal Neural Networks for Deception
Detection." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Workshops (CVPRW 2018), 1–7, DOI: 10.1109/CVPRW.2018.00009.
[20] Ott, M., Choi, Y., Cardie, C., & Hancock, J. T. (2011). "Finding Deceptive Opinion Spam by
Any Stretch of the Imagination." Proceedings of the 49th Annual Meeting of the Association
for Computational Linguistics: Human Language Technologies (ACL-HLT 2011), 309–319, DOI:
10.3115/2002472.2002512.
[21] Perez-Rosas, V., Kleinberg, B., Lefevre, A., & Mihalcea, R. (2018). Automatic Detection of Deception
in Text: A Survey. Computational Linguistics, 44(4), 1–25, DOI: 10.1162/coli_a_00332.
[22] Wang, W. Y. (2017). "Liar, Liar Pants on Fire: A New Benchmark Dataset for Fake News Detection."
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL
2017), 422–426, DOI: 10.18653/v1/P17-2067.
[23] Monaro, M., Gamberini, L., & Sartori, G. (2017). The detection of faked identity using unexpected
questions and mouse dynamics. PLoS ONE, 12(5), 1-13. DOI: 10.1371/journal.pone.017785.
[24] M. J, M. C, B.-G. I, S. N, H. C and I. I, "Learning to Detect Deception," Front. Psycholfrom Evasive
Answers and Inconsistencies across Repeated Interviews: A Study with Lay Respondents and
Police Officers., vol. 8, pp. 1-17, 4 January 2018, DOI: 10.3389/fpsyg.2017.02207.
[25] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8),
1735–1780, DOI: 10.1162/neco.1997.9.8.1735.
[26] Graves, A., & Schmidhuber, J. (2005). Framewise Phoneme Classification with Bidirectional LSTM
Networks. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN),
2047–2052, DOI: 10.1109/IJCNN.2005.1556215.
[27] Bond, C. F., & DePaulo, B. M. (2006). Accuracy of deception judgments. Personality and Social
Psychology Review, 10(3), 214-234. DOI: 10.1207/s15327957pspr1003_2.
[28] E. H. Ndez-Fernaude and M. Alonso-Quecuty, "The Cognitive Interview and Lie Detection: a New
Magnifying Glass for Sherlock Holmes?," APPLIED COGNITIVE PSYCHOLOGY, vol. 11, pp. 55-68,
1997, DOI: 10.1002/(SICI)1099-0720(199702)11:1<55::AID-ACP423>3.0.CO;2-G.
[29] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional
Transformers for Language Understanding. Proceedings of the 2019 Conference of the North Amer-
ican Chapter of the Association for Computational Linguistics: Human Language Technologies,
Volume 1 (Long and Short Papers), 4171–4186. DOI: 10.18653/v1/N19-1423.
[30] Hutto, C. J., & Gilbert, E. (2014). "VADER: A Parsimonious Rule-based Model for Sentiment Analysis
of Social Media Text." Proceedings of the International AAAI Conference on Web and Social Media
(ICWSM), 216–225. DOI: 10.1609/icwsm.v8i1.14550 .
[31] Han, J., Kamber, M., & Pei, J. (2011). Data Mining: Concepts and Techniques (3rd ed.). Morgan
Kaufmann, DOI: 10.1016/C2009-0-61819-5.
[32] Kingma, D. P., & Ba, J. (2015). "Adam: A Method for Stochastic Optimization." Proceedings of the
International Conference on Learning Representations (ICLR). DOI: 10.48550/arXiv.1412.6980.
[33] Prechelt, L. (1998). "Early Stopping—But When?" Neural Networks: Tricks of the Trade (pp.55–69).
Springer. DOI: 10.1007/3-540-49430-8_3.
A. Online Resources
• The LIAR dataset was accessed from LIAR.
• The Deceptive Opinion Spam dataset was accessed from Deceptive Opinion Spam.