Skip to content

An AI-powered Streamlit web app to detect greenwashing in sustainability claims using DistilBERT (MNLI) model. Classifies input text into: Greenwashing, Genuine, or Marketing Hype. Built by Team BharatWin ๐Ÿ‡ฎ๐Ÿ‡ณ.

License

Notifications You must be signed in to change notification settings

Someshog/greenwashing-detection-app

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

17 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐ŸŒฑ Spot the Greenwash: Sustainability Claim Analyzer

Streamlit Model

Overview

Spot the Greenwash Spot the Greenwash is an AI-powered Streamlit app that aids in determining what sustainability claims are true and what is greenwashing in product marketing! By leveraging advanced natural language processing (NLP) and zero-shot classification techniques, the app will enable people to make informed choices on which products they want to buy, that are also environmentally friendly, and challenge companies promises.

Numerous major brands have been criticized for vague or misleading environmental claims โ€” including H&M for its โ€œConsciousโ€ clothing line, Nestlรฉ for its claims about recyclable plastic materials and Volkswagen for its notorious โ€œclean dieselโ€ campaign. This app will help you to question similar claims and cut through the buzzwords.

Whether youโ€™re an eco conscious shopper, environmental advocate, or just curious โ€” this tool makes it easy to fact check green claims, stay informed, and make decisions that actually support planet.


๐Ÿš€ Features

  • Zero-shot claim classification: Detect Greenwashing, Genuine Sustainability, and Marketing Hype
  • Confidence scores: Visualize how strongly a claim matches each category
  • Detailed indicator analysis: See top indicators for each category
  • Example claims: Try the app with built-in sample claims
  • Beautiful UI: Modern, clean, and easy to use
  • About Us section: Learn about the mission and team
  • Future roadmap: Batch analysis, ingredient analysis, report uploads, and more

๐Ÿง  AI Model

  • Model Used: joeddav/distilbert-base-uncased-mnli
  • Method: Zero-shot classification via Hugging Face Transformers
  • Categories:
    • Greenwashing
    • Genuine Sustainability
    • Marketing Hype
  • Indicators: Each category has detailed sub-labels for deeper analysis

๐Ÿ’ป Setup & Installation

  1. Clone the repository
    git clone https://github.com/<your-username>/greenwashing-detection-app.git
    cd greenwashing-detection-app
  2. Install dependencies
    pip install -r requirements.txt
  3. Run the app
    streamlit run app.py

๐Ÿ–ผ๏ธ Screenshots

ss1

๐Ÿ“‹ Example Claims

  • "Our product is eco-friendly and good for the environment."
  • "We use 100% certified organic cotton sourced from fair-trade farms with verified supply chain transparency."
  • "This amazing natural product will revolutionize your life!"
  • "Our revolutionary green technology reduces carbon emissions without any compromise on performance."
  • "Made with sustainable materials that protect the planet for future generations."

๐Ÿ† Why This App Stands Out

  • Real-time AI analysis: Instantly spot misleading claims
  • User-friendly: No technical expertise required
  • Open-source: Transparent and extensible
  • Social impact: Empowers consumers and promotes honest sustainability

๐Ÿ‘ฅ Team & Mission

Built by Team BharatWin

Our Mission:

To democratize access to sustainability information and empower consumers to make informed, environmentally conscious purchasing decisions while holding brands accountable for their environmental claims.

Contact: [email protected]


๐Ÿ“„ License

This project is licensed under the MIT License. See LICENSE for details.


๐Ÿ™Œ Contributing

We welcome contributions! See CONTRIBUTING.md for guidelines.


๐Ÿ’ก Future Roadmap

  • Product ingredient analysis
  • Batch claim analysis
  • Sustainability report uploads
  • Historical tracking of claims

โญ If you like this project, star it on GitHub and share with others!

About

An AI-powered Streamlit web app to detect greenwashing in sustainability claims using DistilBERT (MNLI) model. Classifies input text into: Greenwashing, Genuine, or Marketing Hype. Built by Team BharatWin ๐Ÿ‡ฎ๐Ÿ‡ณ.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages