This project uses the TensorFlow framework and the Keras API to build a classification model for detecting fake news headlines. The model is trained on a dataset of news headlines labeled as either genuine or fake.
The dataset used for training and testing the model consists of news headlines labeled as either genuine or fake.
Before training the model, data preprocessing steps such as tokenization and padding are applied to the input data.
The model consists of an embedding layer and a series of dense layers. The final layer uses a sigmoid activation function to output a probability value between 0 and 1, with 0 indicating a genuine headline and 1 indicating a fake headline.
The model is trained using the Adam optimization algorithm and the binary cross-entropy loss function.
The model is evaluated on a holdout test set and the evaluation metric used is accuracy