An Ensemble Approach for Detection of PersianFake News on COVID-۱۹

The rise of social media has fundamentallychanged how people access news, with online platformsbecoming the primary source of information. COVID-۱۹,caused by the SARS coronavirus ۲, has had a global impact,leading to significant social, economic, and psychologicalchanges worldwide. Recently, there has been a surge in demandfor COVID-۱۹ information on various platforms, but this hasalso given rise to the spread of misinformation on social media.Trusting and sharing false news during a global health crisis canhave serious consequences. To address this challenge, our studyutilizes a dataset of social media news related to COVID-۱۹,meticulously annotated to distinguish between real and fakenews. This study assessed five machine learning and three deeplearning models. Various text representation techniques wereemployed, including term frequency, term frequency-inversedocument frequency, and embeddings. Performance wasevaluated using accuracy, precision, recall, F۱-score, and aKappa test to determine statistical significance. The study alsointroduces an ensemble model with promising results. Thisresearch is crucial in combating the spread of misinformation insocial media and it's not limited to COVID-۱۹ news; thisapproach can be applied to detect fake news in different areas.