Spaces:
Running
Running
| title: Fake News Detector | |
| emoji: 📚 | |
| colorFrom: purple | |
| colorTo: blue | |
| sdk: gradio | |
| sdk_version: 5.33.0 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: 'Detects Fake News using the ensemble of 3 Models ' | |
| # 📚 Fake News Detector | |
| **Detects Fake News using an ensemble of 3 Models (Naive Bayes, Logistic Regression, and GloVe-based embeddings)** | |
| --- | |
| ## 🚨 Important Disclaimer | |
| > ⚠️ This project is built purely for **educational and experimental purposes** to explore basic Natural Language Processing (NLP) and Machine Learning (ML) techniques. | |
| > | |
| > ❗ It is **not suitable for real-world fact-checking or decision-making**. | |
| > | |
| > The models used are simple, non-contextual, and cannot understand language nuances or factual correctness. Misusing this tool for serious analysis may lead to incorrect or harmful conclusions. | |
| > | |
| > **Please do not trust or rely on the outputs of this demo.** It is meant for **learning only.** | |
| --- | |
| ## 🎯 Purpose | |
| This project was created as a part of our research internship as a way to: | |
| - Practice building an ensemble model using different NLP approaches | |
| - Learn to deploy ML apps with Gradio and Hugging Face Spaces | |
| - Experiment with basic text classification on news headlines/articles | |
| It is **not** a robust or reliable system for determining truth or accuracy in media. | |
| --- | |
| ## ⚙️ How It Works | |
| This Fake News Detector uses an ensemble of 3 models: | |
| 1. **Naive Bayes with TF-IDF** – assigns 55% weight | |
| 2. **Logistic Regression** – assigns 10% weight | |
| 3. **GloVe Embedding-Based Classifier** – assigns 35% weight | |
| Each model contributes a score between 0 and 1 indicating the likelihood of the input text being "Real." The final prediction is based on a weighted average. | |
| --- | |
| ## 📄 License & Attribution | |
| This project is licensed under the **MIT License**. | |
| ### Libraries and Tools Used: | |
| - 🧠 [GloVe Embeddings by Stanford NLP](https://nlp.stanford.edu/projects/glove/) | |
| - 🌐 [Gradio Interface Library](https://www.gradio.app/) | |
| - 📚 [scikit-learn](https://scikit-learn.org/) for model implementation | |
| - 🛠 [NLTK](https://www.nltk.org/) for basic NLP preprocessing | |
| - [Dataset](https://www.kaggle.com/datasets/stevenpeutz/misinformation-fake-news-text-dataset-79k) | |
| ## 📦 Installation | |
| ```bash | |
| pip install -r requirements.txt | |
| python app.py | |