Subject

Fake news has become a prevalent issue in today's society, with the rise of social media platforms and the easy dissemination of information online. The spread of misinformation can lead to negative impacts on society, such as election interference, public panic, and even violence. Thus, detecting fake news has become a critical task to ensure that people receive accurate information. In recent years, deep learning techniques have shown promising results in various natural language processing tasks, including fake news detection. In this thesis proposal, we aim to investigate the application of deep learning techniques for fake news detection.

Kind of work

The primary objective of this research is to develop a fake news detection system using deep learning techniques. The specific research objectives are as follows:

1. To review the existing literature on fake news detection and deep learning techniques for natural language processing.
2. To collect and preprocess a dataset of news articles for training and testing the fake news detection system.
3. To implement and compare the performance of different deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based models, for fake news detection.
4. To evaluate the proposed system's performance using various metrics, including accuracy, precision, recall, and F1-score.
5. To perform an extensive analysis of the results and draw conclusions on the effectiveness of deep learning techniques for fake news detection.

Framework of the Thesis

EU CHIST-ERA project CON-NET

Number of Students

1

Expected Student Profile

Good knowledge of Machine Learning, AI and data processing. Good programming skills in Python (particularly PyTorch)