Classifying and fact-checking health-related information about COVID-19 on Twitter/X using machine learning and deep learning models

BMC Medical Informatics and Decision Making, Journal Year: 2025, Volume and Issue: 25(1)

Published: Feb. 11, 2025

Abstract Background Despite recent progress in misinformation detection methods, further investigation is required to develop more robust fact-checking models with particular consideration for the unique challenges of health information sharing. This study aimed identify most effective approach detecting and classifying reliable versus content shared on Twitter/X related COVID-19. Methods We have used 7 different machine learning/deep learning models. Tweets were collected, processed, labeled, analyzed using relevant keywords hashtags, then classified into two distinct datasets: “Trustworthy information” “Misinformation”, through a labeling process. The cosine similarity metric was employed address oversampling minority Trustworthy class, ensuring balanced representation both classes training testing purposes. Finally, performance various compared accuracy, precision, recall, F1-score ROC curve, AUC. Results For measures F1 score, average values TextConvoNet found be 90.28, 90.29, 0.9030, respectively. AUC 0.901.“Trustworthy class achieved an accuracy 85%, precision 93%, recall 86%, score 89%. These higher than other Moreover, its category even impressive, 94%, 88%, 91%. Conclusion showed that trustworthy V.S issues been Twitter/X.

Language: Английский

---

Pclf: Parallel cnn-lstm fusion model for sms spam filtering

BIO Web of Conferences, Journal Year: 2024, Volume and Issue: 97, P. 00136 - 00136

Published: Jan. 1, 2024

Short Message Service (SMS) is widely used for its accessibility, simplicity, and cost-effectiveness in communication, bank notifications, identity confirmation. The increase spam text messages presents significant challenges, including time waste, potential financial scams, annoyance users carriers. This paper proposes a novel deep learning model based on parallel structure the feature extraction step to address this challenge, unlike traditional models that only enhance classifier. fuses local temporal features representation by combining convolutional neural networks (CNN) long short-term memory (LSTM). performance of has been evaluated UCI SMS Collection V.1 dataset, which comprises both ham messages. achieves an accuracy 99.28% dataset. Also, demonstrates good precision, recall, F1 score. aims provide best protection from unwanted mobile phone users.

Language: Английский

---

Shallow Learning Versus Deep Learning in Speech Recognition Applications

Published: Jan. 1, 2024

Language: Английский

---

Two-Channel News Title Classification Model Based on Ernie

Published: Sept. 6, 2024

Language: Английский

---