Fake News Detection using 5L-CNN

With the advent of websites and social media technologies, the internet has been a great method of transmitting news and information around the globe. However, due to lack of editorial scrutiny and monitoring by the media authorities, the news distribution has been seriously abused leading to the fast spreading of fake news. Fake news involves misleading broadcasting of information from sources that target to intentionally manipulate the way how people view some events or statements. This study seeks to develop a fake news detection model which will be able to analyze the title and text information attached to the news articles. From the researches done by previous scholars, it showed that the models did not perform very well because of the lack of sufficient feature extraction and fine tuning of the classification of the text. This research will therefore, articulate the gap by employing 5L-CNN deep learning model which will use inbuilt tokenizers for word embedding and will show better accuracy compared to the traditional machine learning models. In this paper, we compare machine learning algorithms (Decision trees, Random Forest, Logistic Regression & Naive Bayes) and deep learning algorithms (RNN, 5L-CNN & LSTM) to classify the authenticity of news articles. The model developed in this paper attained the best accuracy with 5L-CNN which had a result of 99.99%.