Cargando…

Deepfake tweets classification using stacked Bi-LSTM and words embedding

The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make thei...

Descripción completa

Detalles Bibliográficos
Autores principales: Rupapara, Vaibhav, Rustam, Furqan, Amaar, Aashir, Washington, Patrick Bernard, Lee, Ernesto, Ashraf, Imran
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8576542/
https://www.ncbi.nlm.nih.gov/pubmed/34805502
http://dx.doi.org/10.7717/peerj-cs.745
_version_ 1784595897440534528
author Rupapara, Vaibhav
Rustam, Furqan
Amaar, Aashir
Washington, Patrick Bernard
Lee, Ernesto
Ashraf, Imran
author_facet Rupapara, Vaibhav
Rustam, Furqan
Amaar, Aashir
Washington, Patrick Bernard
Lee, Ernesto
Ashraf, Imran
author_sort Rupapara, Vaibhav
collection PubMed
description The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make their way to social platforms. The polarity of such tweets is significant to determine the sentiment of people about deep fakes. This paper presents a deep learning model to predict the polarity of deep fake tweets. For this purpose, a stacked bi-directional long short-term memory (SBi-LSTM) network is proposed to classify the sentiment of deep fake tweets. Several well-known machine learning classifiers are investigated as well such as support vector machine, logistic regression, Gaussian Naive Bayes, extra tree classifier, and AdaBoost classifier. These classifiers are utilized with term frequency-inverse document frequency and a bag of words feature extraction approaches. Besides, the performance of deep learning models is analyzed including long short-term memory network, gated recurrent unit, bi-direction LSTM, and convolutional neural network+LSTM. Experimental results indicate that the proposed SBi-LSTM outperforms both machine and deep learning models and achieves an accuracy of 0.92.
format Online
Article
Text
id pubmed-8576542
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-85765422021-11-19 Deepfake tweets classification using stacked Bi-LSTM and words embedding Rupapara, Vaibhav Rustam, Furqan Amaar, Aashir Washington, Patrick Bernard Lee, Ernesto Ashraf, Imran PeerJ Comput Sci Artificial Intelligence The spread of altered media in the form of fake videos, audios, and images, has been largely increased over the past few years. Advanced digital manipulation tools and techniques make it easier to generate fake content and post it on social media. In addition, tweets with deep fake content make their way to social platforms. The polarity of such tweets is significant to determine the sentiment of people about deep fakes. This paper presents a deep learning model to predict the polarity of deep fake tweets. For this purpose, a stacked bi-directional long short-term memory (SBi-LSTM) network is proposed to classify the sentiment of deep fake tweets. Several well-known machine learning classifiers are investigated as well such as support vector machine, logistic regression, Gaussian Naive Bayes, extra tree classifier, and AdaBoost classifier. These classifiers are utilized with term frequency-inverse document frequency and a bag of words feature extraction approaches. Besides, the performance of deep learning models is analyzed including long short-term memory network, gated recurrent unit, bi-direction LSTM, and convolutional neural network+LSTM. Experimental results indicate that the proposed SBi-LSTM outperforms both machine and deep learning models and achieves an accuracy of 0.92. PeerJ Inc. 2021-10-21 /pmc/articles/PMC8576542/ /pubmed/34805502 http://dx.doi.org/10.7717/peerj-cs.745 Text en ©2021 Rupapara et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Rupapara, Vaibhav
Rustam, Furqan
Amaar, Aashir
Washington, Patrick Bernard
Lee, Ernesto
Ashraf, Imran
Deepfake tweets classification using stacked Bi-LSTM and words embedding
title Deepfake tweets classification using stacked Bi-LSTM and words embedding
title_full Deepfake tweets classification using stacked Bi-LSTM and words embedding
title_fullStr Deepfake tweets classification using stacked Bi-LSTM and words embedding
title_full_unstemmed Deepfake tweets classification using stacked Bi-LSTM and words embedding
title_short Deepfake tweets classification using stacked Bi-LSTM and words embedding
title_sort deepfake tweets classification using stacked bi-lstm and words embedding
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8576542/
https://www.ncbi.nlm.nih.gov/pubmed/34805502
http://dx.doi.org/10.7717/peerj-cs.745
work_keys_str_mv AT rupaparavaibhav deepfaketweetsclassificationusingstackedbilstmandwordsembedding
AT rustamfurqan deepfaketweetsclassificationusingstackedbilstmandwordsembedding
AT amaaraashir deepfaketweetsclassificationusingstackedbilstmandwordsembedding
AT washingtonpatrickbernard deepfaketweetsclassificationusingstackedbilstmandwordsembedding
AT leeernesto deepfaketweetsclassificationusingstackedbilstmandwordsembedding
AT ashrafimran deepfaketweetsclassificationusingstackedbilstmandwordsembedding