This study evaluates the effectiveness of machine learning (ML) and deep learning (DL) models in detecting COVID-19-related misinformation on online social networks (OSNs), aiming to develop more effective tools for countering the spread of health misinformation during the pan-demic. The study trained and tested various ML classifiers (Naive Bayes, SVM, Random Forest, etc.), DL models (CNN, LSTM, hybrid CNN+LSTM), and pretrained language models (DistilBERT, RoBERTa) on the "COVID19-FNIR DATASET." These models were evaluated for accuracy, F1 score, recall, precision, and ROC, and used preprocessing techniques like stemming and lemmatization. The results showed SVM performed well, achieving a 94.41% F1-score. DL models with Word2Vec embeddings exceeded 98% in all performance metrics (accuracy, F1 score, recall, precision & ROC). The CNN+LSTM hybrid models also exceeded 98% across performance metrics, outperforming pretrained models like DistilBERT and RoBERTa. Our study concludes that DL and hybrid DL models are more effective than conventional ML algorithms for detecting COVID-19 misinformation on OSNs. The findings highlight the importance of advanced neural network approaches and large-scale pretraining in misinformation detection. Future research should optimize these models for various misinformation types and adapt to changing OSNs, aiding in combating health misinformation.

The rapid spread of health misinformation on online social networks (OSNs) during global crises such as the COVID-19 pandemic poses challenges to public health, social stability, and institutional trust. Centrality metrics have long been pivotal in understanding the dynamics of information flow, particularly in the context of health misinformation. However, the increasing complexity and dynamism of online networks, especially during crises, highlight the limitations of these traditional approaches. This study introduces and compares three novel centrality metrics: dynamic influence centrality (DIC), health misinformation vulnerability centrality (MVC), and propagation centrality (PC). These metrics incorporate temporal dynamics, susceptibility, and multilayered network interactions. Using the FibVID dataset, we compared traditional and novel metrics to identify influential nodes, propagation pathways, and misinformation influencers. Traditional metrics identified 29 influential nodes, while the new metrics uncovered 24 unique nodes, resulting in 42 combined nodes, an increase of 44.83%. Baseline interventions reduced health misinformation by 50%, while incorporating the new metrics increased this to 62.5%, an improvement of 25%. To evaluate the broader applicability of the proposed metrics, we validated our framework on a second dataset, Monant Medical Misinformation, which covers a diverse range of health misinformation discussions beyond COVID-19. The results confirmed that the advanced metrics generalised successfully, identifying distinct influential actors not captured by traditional methods. In general, the findings suggest that a combination of traditional and novel centrality measures offers a more robust and generalisable framework for understanding and mitigating the spread of health misinformation in different online network contexts.

Introduction: This study investigates how linguistic features distinguish health misinformation from factual communication in pandemic-related online discourse. Understanding these differences is essential for improving detection of misinformation and informing effective public health messaging during crises.Methods: We conducted a computational linguistic analysis across three corpora: COVID-19 false narratives (n = 7,588), general COVID-19 content (n = 10,700), and Monkeypox-related posts (n = 5,787). We examined readability, rhetorical markers, and persuasive language, focusing on differences between misinformation and factual communication.Results: COVID-19 misinformation exhibited markedly lower readability scores and contained more than twice the frequency of fear-related and persuasive terms compared to the other datasets. It showed minimal use of exclamation marks, contrasting with the more emotive style of Monkeypox content. These findings suggest that misinformation employs a deliberately complex rhetorical style combined with emotional cues, which may enhance perceived credibility.Discussion: Our findings contribute to the growing body of research on digital health misinformation by identifying linguistic indicators that can aid in detection. They also inform theoretical models of crisis communication and public health messaging strategies in networked media environments. However, the study has limitations, including reliance on traditional readability indices, a narrow persuasive lexicon, and static aggregate analysis. Future work should adopt longitudinal designs, incorporate broader emotion lexicons, and employ platform-sensitive approaches to improve robustness. The data and code supporting this study are openly available at: https://doi.org/10.5281/zenodo.17024569.

Health misinformation during the COVID-19 pandemic has significantly challenged public health efforts globally. This study applies the Elaboration Likelihood Model (ELM) to enhance misinformation detection on social media using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model. The model aims to enhance the detection accuracy and reliability of misinformation classification by integrating ELM-based features such as text readability, sentiment polarity, and heuristic cues (e.g., punctuation frequency). The enhanced model achieved an accuracy of 97.37%, precision of 96.88%, recall of 98.50%, F1-score of 97.41%, and ROC-AUC of 99.50%. A combined model incorporating feature engineering further improved performance, achieving a precision of 98.88%, recall of 99.80%, F1-score of 99.41%, and ROC-AUC of 99.80%. These findings highlight the value of ELM features in improving detection performance, offering valuable contextual information. This study demonstrates the practical application of psychological theories in developing advanced machine learning algorithms to address health misinformation effectively.