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 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.

[1]  Aakanksha Sharaff,et al.  Extra-Tree Classifier with Metaheuristics Approach for Email Classification , 2019, Advances in Intelligent Systems and Computing.

[2]  Larry S. Yaeger,et al.  Sentiment Mining Using Ensemble Classification Models , 2008, SCSS.

[3]  J. Friedman Greedy function approximation: A gradient boosting machine. , 2001 .

[4]  Gyu Sang Choi,et al.  Review prognosis system to predict employees job satisfaction using deep neural network , 2021, Comput. Intell..

[5]  Andreas F. Ehmann,et al.  Lyric Text Mining in Music Mood Classification , 2009, ISMIR.

[6]  Andrea Esuli,et al.  SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining , 2010, LREC.

[7]  Ying Su,et al.  Ensemble Learning for Sentiment Classification , 2012, CLSW.

[8]  Feiran Huang,et al.  Attention-Based Modality-Gated Networks for Image-Text Sentiment Analysis , 2020, ACM Trans. Multim. Comput. Commun. Appl..

[9]  Ming Zhou,et al.  Learning Sentiment-Specific Word Embedding for Twitter Sentiment Classification , 2014, ACL.

[10]  Peter D. Turney Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews , 2002, ACL.

[11]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[12]  Mingxi Zhang,et al.  An Empirical Study of TextRank for Keyword Extraction , 2020, IEEE Access.

[13]  B. S. Harish,et al.  Sentiment Analysis on IMDb Movie Reviews Using Hybrid Feature Extraction Method , 2019, Int. J. Interact. Multim. Artif. Intell..

[14]  R. Rajasree,et al.  Sentiment analysis in twitter using machine learning techniques , 2013, 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT).

[15]  Gyu Sang Choi,et al.  Tweets Classification on the Base of Sentiments for US Airline Companies , 2019, Entropy.

[16]  W. Aslam,et al.  A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis , 2021, PloS one.

[17]  Mousa Tayseer Jafar,et al.  Sentiment Analysis-Based Sexual Harassment Detection Using Machine Learning Techniques , 2021, 2021 International Symposium on Electronics and Smart Devices (ISESD).

[18]  J. Yearwood,et al.  Multimodal Deep Learning Framework for Sentiment Analysis from Text-Image Web Data , 2020, 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT).

[19]  Aytug Onan,et al.  A multiobjective weighted voting ensemble classifier based on differential evolution algorithm for text sentiment classification , 2016, Expert Syst. Appl..

[20]  Shahaboddin Shamshirband,et al.  Machine Learning-Based Sentiment Analysis for Twitter Accounts , 2018 .

[21]  Janyce Wiebe,et al.  Articles: Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis , 2009, CL.

[22]  Marshall S. Smith,et al.  The general inquirer: A computer approach to content analysis. , 1967 .

[23]  João Francisco Valiati,et al.  Document-level sentiment classification: An empirical comparison between SVM and ANN , 2013, Expert Syst. Appl..

[24]  Gyu Sang Choi,et al.  GBSVM: Sentiment Classification from Unstructured Reviews Using Ensemble Classifier , 2020, Applied Sciences.

[25]  2021 International Symposium on Electronics and Smart Devices (ISESD) , 2021 .

[26]  Eric P. Xing,et al.  Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2014, ACL 2014.

[27]  Harith Alani,et al.  Contextual semantics for sentiment analysis of Twitter , 2016, Inf. Process. Manag..

[28]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[29]  Vasudeva Varma,et al.  Sentiment classification: a lexical similarity based approach for extracting subjectivity in documents , 2010, Information Retrieval.

[30]  Bei Yu,et al.  An evaluation of text classification methods for literary study , 2008, Lit. Linguistic Comput..

[31]  Kazutaka Shimada,et al.  Movie Review Classification Based on a Multiple Classifier , 2007, PACLIC.

[32]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[33]  James Hays,et al.  Generalization in Metric Learning: Should the Embedding Layer Be Embedding Layer? , 2018, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV).

[34]  Andrei O. J. Kwok,et al.  Deepfake: a social construction of technology perspective , 2020, Current Issues in Tourism.

[35]  Ewan Klein,et al.  Web Intelligence and Intelligent Agent Technology (WI-IAT) , 2012 .

[36]  Gyu Sang Choi,et al.  Wireless Capsule Endoscopy Bleeding Images Classification Using CNN Based Model , 2021, IEEE Access.

[37]  Huimin Zhao,et al.  Adapting sentiment lexicons to domain-specific social media texts , 2017, Decis. Support Syst..

[38]  Prabhat Ranjan,et al.  Proposed Approach for Sarcasm Detection in Twitter , 2017 .

[39]  Maite Taboada,et al.  Lexicon-Based Methods for Sentiment Analysis , 2011, CL.

[40]  Yoav Freund,et al.  A Short Introduction to Boosting , 1999 .

[41]  I. Ashraf,et al.  Determining the Efficiency of Drugs Under Special Conditions From Users’ Reviews on Healthcare Web Forums , 2021, IEEE Access.

[42]  Pedro Larrañaga,et al.  Supervised classification with conditional Gaussian networks: Increasing the structure complexity from naive Bayes , 2006, Int. J. Approx. Reason..

[43]  Georgia,et al.  Generalization in Metric Learning: Should the Embedding Layer be Embedding Layer? , 2018 .

[44]  Ram Mohana Reddy Guddeti,et al.  Influence factor based opinion mining of Twitter data using supervised learning , 2014, 2014 Sixth International Conference on Communication Systems and Networks (COMSNETS).

[45]  Gyu Sang Choi,et al.  Impact of SMOTE on Imbalanced Text Features for Toxic Comments Classification Using RVVC Model , 2021, IEEE Access.

[46]  Bernhard Schölkopf,et al.  Incorporating Invariances in Support Vector Learning Machines , 1996, ICANN.

[47]  Fangzhao Wu,et al.  Microblog sentiment classification with heterogeneous sentiment knowledge , 2016, Inf. Sci..

[48]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[49]  M. Westerlund The Emergence of Deepfake Technology: A Review , 2019, Technology Innovation Management Review.

[50]  Philip Treleaven,et al.  Twitter Sentiment Analysis , 2015, ArXiv.

[51]  Janyce Wiebe,et al.  RECOGNIZING STRONG AND WEAK OPINION CLAUSES , 2006, Comput. Intell..

[52]  N. Prasath,et al.  Opinion mining and sentiment analysis on a Twitter data stream , 2012, International Conference on Advances in ICT for Emerging Regions (ICTer2012).

[53]  W. Copes,et al.  Evaluating trauma care: the TRISS method. Trauma Score and the Injury Severity Score. , 1987, The Journal of trauma.

[54]  Tiago A. Almeida,et al.  Short text opinion detection using ensemble of classifiers and semantic indexing , 2016, Expert Syst. Appl..

[55]  Konstantin A. Pantserev,et al.  The Malicious Use of AI-Based Deepfake Technology as the New Threat to Psychological Security and Political Stability , 2020 .

[56]  Li Zhang,et al.  Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer , 2020, IEEE Access.

[57]  Jian Ma,et al.  Sentiment classification: The contribution of ensemble learning , 2014, Decis. Support Syst..