An ML-powered classifier to distinguish between human-generated and AI-generated comments on social media, using machine learning techniques for accurate detection and analysis
This project is designed to classify social media comments as either human-generated or AI-generated. Using machine learning techniques, the classifier aims to accurately distinguish between the two types of content, focusing on key text features and model evaluation metrics.
- Data Preprocessing: Cleans and prepares text data for model training.
- Modeling: Implements a logistic regression model for binary classification.
- Evaluation: Utilizes precision, recall, F1-score, and other metrics to evaluate model performance.
To run this project locally, follow these steps:
-
Clone the repository:
git clone https://github.com/yourusername/AI-Comment-Classifier.git cd AI-Comment-Classifier -
Install dependencies:
pip install -r requirements.txt
-
Prepare your dataset:
- Ensure your data is in a CSV format with the appropriate labels (human-generated or AI-generated).
-
Run the model:
- Use the provided scripts to train the model on your dataset.
- Evaluate the results using the included evaluation functions.
-
Example Command:
python train_model.py --data data/comments.csv
- data/: Sample datasets used for training and testing.
- src/: Contains the main code files, including preprocessing, modeling, and evaluation scripts.
- notebooks/: Jupyter notebooks for exploratory data analysis and model experimentation.
- app.py: Flask application python file
- .pkl files: Needed for flask application to use trained model
- templates/index.html: Base HTML UI file
- requirements.txt: List of dependencies required to run the project.
If you would like to contribute to this project, feel free to fork the repository and submit a pull request.
This project is licensed under the MIT License. See the LICENSE file for more details.
For any questions or suggestions, please contact Salil Apte / Surya Ammisetti / Shrinidhi Sivakumar
