Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach

This paper presents a novel algorithm that leverages cutting-edge machine-learning techniques to accurately and efficiently detect AI-generated texts. Rapid advancements in natural language processing models have led to the generation of text closely resembling human language, making it increasingly...

Full description

Saved in:
Bibliographic Details
Main Authors: John Blake, Abu Saleh Musa Miah, Krzysztof Kredens, Jungpil Shin
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10971184/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849311242177478656
author John Blake
Abu Saleh Musa Miah
Krzysztof Kredens
Jungpil Shin
author_facet John Blake
Abu Saleh Musa Miah
Krzysztof Kredens
Jungpil Shin
author_sort John Blake
collection DOAJ
description This paper presents a novel algorithm that leverages cutting-edge machine-learning techniques to accurately and efficiently detect AI-generated texts. Rapid advancements in natural language processing models have led to the generation of text closely resembling human language, making it increasingly difficult to differentiate between human and AI-generated content. However, misuse of such texts presents a serious and imminent threat to the quality of academic publishing. This underscores the urgent need for robust detection mechanisms to ensure information quality, maintain trust, and preserve the integrity of research publications. Our proposed model outperformed existing algorithms for accuracy with less computational complexity. The proposed model is a feature-based hybrid deep learning network that leverages part-of-speech tagging and integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks with Attention modules. The initial module extracts local contextual features using convolutional layers, followed by Bi-LSTM layers that capture long-term dependencies from past and future sequences. An attention mechanism highlights critical sequence components, enhancing the model’s focus on relevant data. The outputs from the attention and initial modules are concatenated through a residual connection, ensuring comprehensive feature representation. This combination is then fed into dense layers for final classification, effectively balancing feature richness and computational efficiency. The proposed model was evaluated on two benchmark datasets, achieving 85.00% and 88.00% accuracy, respectively.
format Article
id doaj-art-37ebe036f23e48828e2b48161097f7fd
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-37ebe036f23e48828e2b48161097f7fd2025-08-20T03:53:28ZengIEEEIEEE Access2169-35362025-01-0113715637157610.1109/ACCESS.2025.356275010971184Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based ApproachJohn Blake0https://orcid.org/0000-0002-3150-4995Abu Saleh Musa Miah1https://orcid.org/0000-0002-1238-0464Krzysztof Kredens2Jungpil Shin3https://orcid.org/0000-0002-7476-2468School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanAston Institute for Forensic Linguistics, Aston University, Birmingham, U.K.School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, JapanThis paper presents a novel algorithm that leverages cutting-edge machine-learning techniques to accurately and efficiently detect AI-generated texts. Rapid advancements in natural language processing models have led to the generation of text closely resembling human language, making it increasingly difficult to differentiate between human and AI-generated content. However, misuse of such texts presents a serious and imminent threat to the quality of academic publishing. This underscores the urgent need for robust detection mechanisms to ensure information quality, maintain trust, and preserve the integrity of research publications. Our proposed model outperformed existing algorithms for accuracy with less computational complexity. The proposed model is a feature-based hybrid deep learning network that leverages part-of-speech tagging and integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks with Attention modules. The initial module extracts local contextual features using convolutional layers, followed by Bi-LSTM layers that capture long-term dependencies from past and future sequences. An attention mechanism highlights critical sequence components, enhancing the model’s focus on relevant data. The outputs from the attention and initial modules are concatenated through a residual connection, ensuring comprehensive feature representation. This combination is then fed into dense layers for final classification, effectively balancing feature richness and computational efficiency. The proposed model was evaluated on two benchmark datasets, achieving 85.00% and 88.00% accuracy, respectively.https://ieeexplore.ieee.org/document/10971184/AI-generated text detectionauthorship analysisauthorship verificationmachine-generated text detection
spellingShingle John Blake
Abu Saleh Musa Miah
Krzysztof Kredens
Jungpil Shin
Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
IEEE Access
AI-generated text detection
authorship analysis
authorship verification
machine-generated text detection
title Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
title_full Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
title_fullStr Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
title_full_unstemmed Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
title_short Detection of AI-Generated Texts: A Bi-LSTM and Attention-Based Approach
title_sort detection of ai generated texts a bi lstm and attention based approach
topic AI-generated text detection
authorship analysis
authorship verification
machine-generated text detection
url https://ieeexplore.ieee.org/document/10971184/
work_keys_str_mv AT johnblake detectionofaigeneratedtextsabilstmandattentionbasedapproach
AT abusalehmusamiah detectionofaigeneratedtextsabilstmandattentionbasedapproach
AT krzysztofkredens detectionofaigeneratedtextsabilstmandattentionbasedapproach
AT jungpilshin detectionofaigeneratedtextsabilstmandattentionbasedapproach