xai-text-classifier 0.1.3.1

A library to explain whether text is AI-generated or human-written using SHAP

XAI Text Classifier

A library to explain whether text is AI-generated or human-written using SHAP (SHapley Additive exPlanations).

Features

• AI vs Human Text Classification: Distinguish between AI-generated and human-written text
• Explainability: Uses SHAP to provide detailed feature importance explanations
• Multiple Models: Includes XGBoost and Random Forest models for robust predictions
• Comprehensive Feature Analysis: Analyzes 40+ linguistic features including:
  • Readability metrics
  • Sentiment analysis
  • Syntactic complexity
  • Stylistic patterns
  • And more

Installation

pip install xai-text-classifier

Or install from source:

git clone <repository-url>
cd xai-text-classifier
pip install -e .

Usage

from xai import shap_explainer

# Analyze text
text = "Your text here..."
result = shap_explainer(text)

# Returns:
# {
#     "prediction": 0 or 1,  # 0 = Human, 1 = AI
#     "features": {
#         "feature_name": {
#             "value": feature_value,
#             "shap_value": shap_contribution,
#             "importance": relative_importance
#         },
#         ...
#     }
# }

Requirements

• Python >= 3.8
• joblib
• shap
• xgboost
• spacy
• language-tool-python
• textblob
• pandas
• numpy
• scikit-learn
• nltk
• textstat
• matplotlib
• scipy

Development

Install development dependencies:

pip install -e ".[dev]"

Run tests:

pytest

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you use this library in your research, please cite:

@software{xai_text_classifier,
  title={XAI Text Classifier},
  year={2025},
  url={<repository-url>}
}