Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach

Abstract With the growth of social media, people are sharing more content than ever, including X posts that reflect a variety of emotions and opinions. AI-generated synthetic text, known as deepfake text, is used to imitate human writing to disseminate misleading information and fake news. However,...

Full description

Saved in:
Bibliographic Details
Main Authors: Madiha Khalid, Muhammad Faheem Mushtaq, Urooj Akram, Mejdl Safran, Sultan Alfarhood, Imran Ashraf
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-10661-3
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766486493626368
author Madiha Khalid
Muhammad Faheem Mushtaq
Urooj Akram
Mejdl Safran
Sultan Alfarhood
Imran Ashraf
author_facet Madiha Khalid
Muhammad Faheem Mushtaq
Urooj Akram
Mejdl Safran
Sultan Alfarhood
Imran Ashraf
author_sort Madiha Khalid
collection DOAJ
description Abstract With the growth of social media, people are sharing more content than ever, including X posts that reflect a variety of emotions and opinions. AI-generated synthetic text, known as deepfake text, is used to imitate human writing to disseminate misleading information and fake news. However, as deepfake technology continues to grow, it becomes harder to accurately understand people’s opinions on deepfake posts. Existing sentiment analysis algorithms frequently fail to capture the domain-specific, misleading, and context-sensitive characteristics of deepfake-related content. This study proposes a hybrid deep learning (DL) approach and novel transfer learning (TL)-based feature extraction approach for deepfake posts’ sentiment analysis. The transfer learning-based approach combines the strengths of the hybrid DL technique to capture global and local contextual information. In this study, we compare the proposed approach with a range of machine learning algorithms, as well as, DL techniques for validation. Different feature extraction techniques, such as a bag of words (BOW), term frequency-inverse document frequency (TF-IDF), word embedding features, and novel TL features that combine the LSTM and DT, are used to build the models. The ML models are fine-tuned with extensive hyperparameter tuning to enhance performance and efficiency. The sentiment analysis performance of each applied method is validated using the k-fold cross-validation. The experimental results indicate that the proposed LGR (LSTM+GRU+RNN) approach with novel TL features performs well with a 99% accuracy. The proposed approach helps detect and prevent the spread of deepfake content, keeping people and organizations safe from its negative effects. This study covers a crucial gap in evaluating deepfake-specific social media sentiment by providing a comprehensive, scalable mechanism for monitoring and reducing the effect of fake content online.
format Article
id doaj-art-beba3319d96441aabd7bf22f50ebf663
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-beba3319d96441aabd7bf22f50ebf6632025-08-20T03:04:34ZengNature PortfolioScientific Reports2045-23222025-08-0115112110.1038/s41598-025-10661-3Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approachMadiha Khalid0Muhammad Faheem Mushtaq1Urooj Akram2Mejdl Safran3Sultan Alfarhood4Imran Ashraf5Faculty of Computing, The Islamia University of BahawalpurFaculty of Computing, The Islamia University of BahawalpurFaculty of Computing, The Islamia University of BahawalpurResearch Chair of Online Dialogue and Cultural Communication, Department of Computer Science, College of Computer and Information Sciences, King Saud UniversityDepartment of Computer Science, College of Computer and Information Sciences, King Saud UniversityDepartment of Information and Communication Engineering, Yeungnam UniversityAbstract With the growth of social media, people are sharing more content than ever, including X posts that reflect a variety of emotions and opinions. AI-generated synthetic text, known as deepfake text, is used to imitate human writing to disseminate misleading information and fake news. However, as deepfake technology continues to grow, it becomes harder to accurately understand people’s opinions on deepfake posts. Existing sentiment analysis algorithms frequently fail to capture the domain-specific, misleading, and context-sensitive characteristics of deepfake-related content. This study proposes a hybrid deep learning (DL) approach and novel transfer learning (TL)-based feature extraction approach for deepfake posts’ sentiment analysis. The transfer learning-based approach combines the strengths of the hybrid DL technique to capture global and local contextual information. In this study, we compare the proposed approach with a range of machine learning algorithms, as well as, DL techniques for validation. Different feature extraction techniques, such as a bag of words (BOW), term frequency-inverse document frequency (TF-IDF), word embedding features, and novel TL features that combine the LSTM and DT, are used to build the models. The ML models are fine-tuned with extensive hyperparameter tuning to enhance performance and efficiency. The sentiment analysis performance of each applied method is validated using the k-fold cross-validation. The experimental results indicate that the proposed LGR (LSTM+GRU+RNN) approach with novel TL features performs well with a 99% accuracy. The proposed approach helps detect and prevent the spread of deepfake content, keeping people and organizations safe from its negative effects. This study covers a crucial gap in evaluating deepfake-specific social media sentiment by providing a comprehensive, scalable mechanism for monitoring and reducing the effect of fake content online.https://doi.org/10.1038/s41598-025-10661-3DeepfakeTransfer learningDeep learningMachine learningFeature engineeringLexicon sentiment analysis
spellingShingle Madiha Khalid
Muhammad Faheem Mushtaq
Urooj Akram
Mejdl Safran
Sultan Alfarhood
Imran Ashraf
Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
Scientific Reports
Deepfake
Transfer learning
Deep learning
Machine learning
Feature engineering
Lexicon sentiment analysis
title Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
title_full Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
title_fullStr Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
title_full_unstemmed Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
title_short Sentiment analysis for deepfake X posts using novel transfer learning based word embedding and hybrid LGR approach
title_sort sentiment analysis for deepfake x posts using novel transfer learning based word embedding and hybrid lgr approach
topic Deepfake
Transfer learning
Deep learning
Machine learning
Feature engineering
Lexicon sentiment analysis
url https://doi.org/10.1038/s41598-025-10661-3
work_keys_str_mv AT madihakhalid sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach
AT muhammadfaheemmushtaq sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach
AT uroojakram sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach
AT mejdlsafran sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach
AT sultanalfarhood sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach
AT imranashraf sentimentanalysisfordeepfakexpostsusingnoveltransferlearningbasedwordembeddingandhybridlgrapproach