News Authenticity Analyzer Using Deep Learning
Year: 2025
Type: article
Abstract: Media serves a crucial function in sharing information about events with the. The swift advancement of the Internetfacilitates rapid information exchange via social media platforms and websites. Often, information is disseminatedwithout verifying its authenticity, permitting unverified or false news to circulate widely on social networks, reachingcountless individuals. Typically, fake news is created to serve commercial and political agendas, aiming to misleadaudiences and garner attention. This proliferation of false information poses a significant challenge for society. Currentresearch is focused on the automatic credibility assessment of news articles. The growth of information andcommunication technologies has dramatically expanded Internet accessibility, altering the way people consumeinformation. Consequently, the rise of fake news has become a pressing issue due to its capability to disruptgovernments, posing a serious threat to modern society. An illustration of this can be seen in the United States duringthe electoral campaign, where the phrase “fake news” gained considerable prominence, largely owing to the impactof falsehoods on the elections' outcomes. This study explores the potential of employing deep learning methods todistinguish fake news online based solely on textual content. Deep learning models are extensively utilized in linguisticmodelling, with Long Short-Term Memory (LSTM) being a tree-structured recurrent neural network designed foranalysing sequential data of varying lengths.
Authors: Mrs. Shilpa Rajole, Pallati Siddharth, Yata Manish, Durgam Ashruth Goud, Pidamarthi Sunil Kumar
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W6911970383
FWCI:
Cites:
Cited by:
Related to: