• Devireddy Pravallika
• S. Kanthi Kiran

Fake news is a kind of false information to intentionally mislead or manipulate public opinion, through conventional mass media and ongoing social media. In recent years, due to explosive growth of online social media, fake news for different political agenda and commercial gains has been coming out in wide spread online. The main objective of the proposed method is to effectively detect fake news and prevent its diffusion on social media which has gained much attention in recent years. Here we also include latent sentiments hidden in user comments which can help to distinguish fake news from reliable content. We incorporate these latent sentiments into deep embedding framework (Multi-Layer Perceptron) for detecting fake news. First, we use multi modal networks to deal with heterogeneous data modalities. Second, to learn semantically meaningful spaces per data source, an adversarial mechanism is adopted. Third, we characterize a novel regularization loss to bring embeddings of relevant pairs closer. The real-world dataset used is PolitiFact, demonstrates the effectiveness in detecting fake news.

Adversarial Mechanism, Fake news, Latent Semantics, Multi-modal networks, Social Media.

"A NOVEL APPROACH FOR DETECTING FAKE NEWS THROUGH MULTI LAYER PERCEPTRON INCLUDING SENTIMENTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 11, page no.694-701, November-2020, Available :http://www.jetir.org/papers/JETIR2011230.pdf

"A NOVEL APPROACH FOR DETECTING FAKE NEWS THROUGH MULTI LAYER PERCEPTRON INCLUDING SENTIMENTS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 11, page no. pp694-701, November-2020, Available at : http://www.jetir.org/papers/JETIR2011230.pdf