Dhinesh Reddy Gundam

Efficient Fake News Detection using Deep Learning

In the era of social networks, the quick rotation of news makes it challenging to promptly evaluate its reliability. The surge in the spread of misleading information, lies, propaganda, and false facts, frequently known as fake news, raised questions concerning social media's influence in today's fast-moving democratic society. The widespread and rapid dissemination of fake news cost us in many ways. For example, individual or societal costs by hampering elections integrity, significant economic losses by impacting stock markets, or increases the risk to national security. The effects of fake news have increased exponentially in the recent past. Something must be done to prevent this from continuing in the future. To address this issue, automated fake news detection tools have become a crucial necessity. Our goal is to propose a Deep Learning model that can be used to check whether the given news article is fake or not. In this project, a Hybrid Neural Network architecture that combines CNN and LSTM capabilities is implemented. We used word cloud to understand the data distribution in the data set. We used word embedding (GloVe) for text preprocessing (stop words removal and lemmatization) to construct a vector space of words and establish a lingual relationship. The data set for training and testing the model were acquired from Kaggle. To this end, we have implemented an initial model of proposed approach; currently, we are working on improving it for better and efficient detection of fake news in real-time.