Deepfake tweets classification using stacked Bi-LSTM and words embedding

Rupapara, Vaibhav; Rustam, Furqan; Amaar, A.; Washington, Patrick Bernard; Lee, Ernesto; Ashraf, Imran

doi:10.7717/peerj-cs.745

Cited by 33 publications

(26 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, the study in [ 53 ] used an extra tree classifier (ETC) for the same task. In addition, the study in [ 54 ] used the CNN-LSTM model for sarcasm detection, and the study in [ 55 ] has performed sentiment analysis using the stacked Bi-LSTM model. For a fair comparison, these models were deployed using the COVID-19 vaccination tweets dataset that was collected in this study.…”

Section: Resultsmentioning

confidence: 99%

COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset

et al. 2022

Self Cite

View full text Add to dashboard Cite

COVID-19 pandemic has caused a global health crisis, resulting in endless efforts to reduce infections, fatalities, and therapies to mitigate its after-effects. Currently, large and fast-paced vaccination campaigns are in the process to reduce COVID-19 infection and fatality risks. Despite recommendations from governments and medical experts, people show conceptions and perceptions regarding vaccination risks and share their views on social media platforms. Such opinions can be analyzed to determine social trends and devise policies to increase vaccination acceptance. In this regard, this study proposes a methodology for analyzing the global perceptions and perspectives towards COVID-19 vaccination using a worldwide Twitter dataset. The study relies on two techniques to analyze the sentiments: natural language processing and machine learning. To evaluate the performance of the different lexicon-based methods, different machine and deep learning models are studied. In addition, for sentiment classification, the proposed ensemble model named long short-term memory-gated recurrent neural network (LSTM-GRNN) is a combination of LSTM, gated recurrent unit, and recurrent neural networks. Results suggest that the TextBlob shows better results as compared to VADER and AFINN. The proposed LSTM-GRNN shows superior performance with a 95% accuracy and outperforms both machine and deep learning models. Performance analysis with state-of-the-art models proves the significance of the LSTM-GRNN for sentiment analysis.

show abstract

Section: Resultsmentioning

confidence: 99%

COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The BoW is simple to use and easy to implement for finding the features from raw text data ( Rustam et al, 2021 ; Rupapara et al, 2021a ). Many language modeling and text classification problems can be solved using the BoW features.…”

Section: Methodsmentioning

confidence: 99%

Classification of movie reviews using term frequency-inverse document frequency and optimized machine learning algorithms

Naeem

Rustam

Mehmood

et al. 2022

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

The Internet Movie Database (IMDb), being one of the popular online databases for movies and personalities, provides a wide range of movie reviews from millions of users. This provides a diverse and large dataset to analyze users’ sentiments about various personalities and movies. Despite being helpful to provide the critique of movies, the reviews on IMDb cannot be read as a whole and requires automated tools to provide insights on the sentiments in such reviews. This study provides the implementation of various machine learning models to measure the polarity of the sentiments presented in user reviews on the IMDb website. For this purpose, the reviews are first preprocessed to remove redundant information and noise, and then various classification models like support vector machines (SVM), Naïve Bayes classifier, random forest, and gradient boosting classifiers are used to predict the sentiment of these reviews. The objective is to find the optimal process and approach to attain the highest accuracy with the best generalization. Various feature engineering approaches such as term frequency-inverse document frequency (TF-IDF), bag of words, global vectors for word representations, and Word2Vec are applied along with the hyperparameter tuning of the classification models to enhance the classification accuracy. Experimental results indicate that the SVM obtains the highest accuracy when used with TF-IDF features and achieves an accuracy of 89.55%. The sentiment classification accuracy of the models is affected due to the contradictions in the user sentiments in the reviews and assigned labels. For tackling this issue, TextBlob is used to assign a sentiment to the dataset containing reviews before it can be used for training. Experimental results on TextBlob assigned sentiments indicate that an accuracy of 92% can be obtained using the proposed model.

show abstract

“…When only one split is implemented in a DT, the Decision Stump operator is utilized. The tree's structure can be applied to categorise previously undiscovered cases [21][22][23][24]. Each branch (to another decision tree) represents a potential attribute value, whereas the decision node represents an attribute test.…”

Section: Decision Stump (Ds)mentioning

confidence: 99%

A Hybrid Model Integrating Adaboost Approach for Sentimental Analysis of Airline Tweets

Yadu¹,

Shukla²

2022

RIA

View full text Add to dashboard Cite

Sentimental Analysis has grown as a significant opinion strategy in the field of online media due to quick information development and internet technologies. This research will play an important role for recommendation of best airline for Indian passengers to prefer the appropriate airline for their journey and also useful for the Indian ministry of aviation. In this study we have gathered different tiny texts called comments from different social media traveling websites using webharvy data fetcher scraping tool related to six top rated Indian airlines. The main problem with airline tweet SA (sentimental analysis) is determining the best sentiment classifier for appropriately classifying the tweets. VADER model has used sentiment ratings to connect lexical characteristics to emotion intensities. In this research, a Hybrid model integrated Adaboost approach (HMIAA) has proposed, which combines the basic learning classifier SVM with the forward-learning ensemble method Gradient Boosted Tree to form a single robust classifier or model, with the objective of improving SCT (sentimental classification technique) efficiency (performance) and accuracy. The findings reveal that the suggested hybrid approach integrating Adaboost technique outperforms other basic classifiers. After completion of sentimental analysis of all datasets we can recommend the passengers for the best airline.

show abstract

Deepfake tweets classification using stacked Bi-LSTM and words embedding

Cited by 33 publications

References 35 publications

COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset

COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset

Classification of movie reviews using term frequency-inverse document frequency and optimized machine learning algorithms

A Hybrid Model Integrating Adaboost Approach for Sentimental Analysis of Airline Tweets

Contact Info

Product

Resources

About