Overview / Usage

The Fake News Detection Project by MachineMinds from MIT Manipal, developed as part of the Intel Unnati initiative, aims to combat the growing problem of misinformation and fake news in the digital age. By leveraging artificial intelligence, the project detects and classifies news articles as fake or real, ensuring more reliable information dissemination. This research is useful for media agencies, social platforms, and individual users to verify the authenticity of news before consumption or sharing.

Methodology / Approach

The project uses natural language processing (NLP) techniques and machine learning algorithms to analyze text data for patterns and features that distinguish fake news from genuine articles. Key steps in the methodology include:

1. Data Collection: Aggregating a dataset of labeled fake and real news articles.
2. Preprocessing: Tokenization, stopword removal, lemmatization, and vectorization using techniques like TF-IDF or word embeddings.
3. Model Development: Training machine learning models such as Logistic Regression, Random Forest, or advanced deep learning models like LSTMs or transformers (e.g., BERT).
4. Validation and Testing: Evaluating model performance using accuracy, precision, recall, and F1-score.
5. Deployment: Integrating the model into a user-friendly application or API for real-time news verification.

Technologies Used

• Programming Language: Python
• Frameworks/Libraries: TensorFlow, PyTorch, Scikit-learn, NLTK, Spacy
• Data Processing: Pandas, NumPy
• Visualization: Matplotlib, Seaborn
• Intel Technologies: Utilization of Intel AI hardware or optimized libraries for faster model training and deployment
• Additional Tools: Jupyter Notebooks for prototyping and testing

Repository

https://github.com/zaidk2021/Intel-Unnati-Project-Fake-News-Detection-MachineMinds-MITManipal

Other links

• Video 1-Fake News Detection Using ML
• Video 2-Fake News Classifier Using LSTM