Andere Kunden interessierten sich auch für
![Comparing Supervised & Unsupervised ML for Fake News Detection]( "Comparing Supervised & Unsupervised ML for Fake News Detection")
Comparing Supervised & Unsupervised ML for Fake News Detection29,99 €![Fake News Detection using Various Computational Techniques]( "Fake News Detection using Various Computational Techniques")
Fake News Detection using Various Computational Techniques29,99 €![Prediction of Liver Cirrhosis Using Machine Learning]( "Prediction of Liver Cirrhosis Using Machine Learning")
Prediction of Liver Cirrhosis Using Machine Learning33,99 €![Design of Paddy Crop Production Technique]( "Design of Paddy Crop Production Technique")
Design of Paddy Crop Production Technique26,99 €![Previsione della cirrosi epatica con l'apprendimento automatico]( "Previsione della cirrosi epatica con l'apprendimento automatico")
Previsione della cirrosi epatica con l'apprendimento automatico33,99 €![Erkennung von Fake News mit verschiedenen Computertechniken]( "Erkennung von Fake News mit verschiedenen Computertechniken")
Erkennung von Fake News mit verschiedenen Computertechniken43,90 €![Previsão da cirrose hepática utilizando a aprendizagem mecânica]( "Previsão da cirrose hepática utilizando a aprendizagem mecânica")
Previsão da cirrose hepática utilizando a aprendizagem mecânica33,99 €
The continuous growth of social media has provided users with more convenient way to access news than even before, and then it is possible that some misinformation or rumours are generated and spread throughout the web, leading others users to believe and propagate them as unintentional lies. This work proposes a model to identify fake news on the social media. The classification of news is based on the level of similarity between the semantic meaning and similar wording of their text. These word vectors of the body and head are used to discover the semantic similarity of words, we propose a feed forward neural network architecture to detect semantically equivalent news. The proposed NN first transforms words into word embeddings, using a large collection of unlabeled data, and then applies a feed forward network to build vector representations for head and body. We will analyze and run our experiments to predict the fake news by using Machine learning and neural network.