查看文章

Fake news is a publicity or conspiracy that contains cautious or fake information having a social as well as political impact because it is spread through old fashioned media and gets the progression via social or news media. Some challenges during fake news are veracity of a news story and natural language processing. This article we are using multimodal approach with Convolutional Neural Network (CNN) and Long Short-Term memory (LSTM) to classify the fake news articles achieved significance performance. We worked on a database with 12 different categories of news articles and used linguistic cue approaches with machine learning. We classified a news based on its source and its previous history (such as domain name and/or author name) with bimodal CNN and LSTM. Through reputable news source, our model classifiesreliable news articles with the accuracy of 99.7% on the training data and 97.5% on test data. However, as a fake news can still be published on a reputable domain, we still had to consider other parameter such as news headlines.