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

  • سال انتشار: 1402
  • محل انتشار: اولین کنفرانس ملی هوش مصنوعی و مهندسی نرم افزار
  • کد COI اختصاصی: AISOFT01_044
  • زبان مقاله: انگلیسی
  • تعداد مشاهده: 216
دانلود فایل این مقاله

نویسندگان

Arezoo Zareian

Computer Science and EngineeringDepartmentShiraz UniversityShiraz, Iran

Melika Zare

Computer Science and EngineeringDepartmentShiraz UniversityShiraz, Iran

Sattar Hashemi

Computer Science and EngineeringDepartmentShiraz UniversityShiraz, Iran

چکیده

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.

کلیدواژه ها

COVID-۱۹, deep learning, ensemble learning,fake news detection, machine learning, Persian fake news

مقالات مرتبط جدید

اطلاعات بیشتر در مورد COI

COI مخفف عبارت CIVILICA Object Identifier به معنی شناسه سیویلیکا برای اسناد است. COI کدی است که مطابق محل انتشار، به مقالات کنفرانسها و ژورنالهای داخل کشور به هنگام نمایه سازی بر روی پایگاه استنادی سیویلیکا اختصاص می یابد.

کد COI به مفهوم کد ملی اسناد نمایه شده در سیویلیکا است و کدی یکتا و ثابت است و به همین دلیل همواره قابلیت استناد و پیگیری دارد.