Aswini-P22

Aswini-P22 / Fake-News-detection-knowledge-graph

Public

Fake News Detection system using Machine Learning, NLP, Named Entity Recognition, Relation Extraction, Knowledge Graphs, and Community/Centrality Analysis with Streamlit UI.

50
0
80% credibility
Found Feb 07, 2026 at 23 stars 2x -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Jupyter Notebook
AI Summary

An interactive web app that analyzes news articles to detect fakes, extracts key entities and relationships, and visualizes them as a graph for better understanding.

How It Works

1
🔍 Discover the fake news checker

You find this handy tool online that helps spot fake news by looking at the story's details and connections.

2
📥 Get it ready on your computer

Download the files and follow simple steps to prepare the news checker so it's all set up for you.

3
🚀 Launch the app

Open the app in your web browser and see a welcoming screen ready for your news story.

4
📝 Paste your news article

Copy and paste the text from a news story into the box, just like typing a note.

5
🔎 Click to analyze

Hit the analyze button and watch as it quickly checks if the news is real or fake, showing confidence and key facts.

6
🕸️ Explore the insights

See highlighted people, places, and how they connect in a simple map, helping you understand why it's fake or real.

✅ Stay informed confidently

You now know the truth about the news and feel smarter about spotting tricks in stories.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 23 to 50 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Fake-News-detection-knowledge-graph?

This Python project delivers an end-to-end fake news detection system that classifies article text as real or fake, using machine learning classifiers like Random Forest alongside NLP for named entity recognition and relation extraction. It builds knowledge graphs from the content, runs community detection and centrality analysis, and surfaces everything in a Streamlit web app where you input text and get predictions, confidence scores, entity lists, relation tables, and interactive graphs. It solves the fake news problem by adding interpretability to high-accuracy classification (99.9% on benchmarks), helping spot misinformation like fake news 2025 trends or fake GitHub activity.

Why is it gaining traction?

Unlike basic text classifiers, it hooks users with visual explainability—knowledge graphs reveal entity networks, influential nodes via centrality, and thematic communities, making "why fake" tangible. The one-command Streamlit launch (`streamlit run app`) lets devs demo instantly without setup hassle, standing out for prototyping fake news finder tools or quizzes. Solid performance and modularity draw forks for tweaks like fake GitHub commit history detection.

Who should use this?

Data scientists prototyping explainable NLP pipelines for news moderation apps. ML researchers testing knowledge graph enhancements on fake news detection using knowledge graph and graph convolutional network ideas. Indie devs building Streamlit dashboards for fake news test tools or spotting fake GitHub profiles in social feeds.

Verdict

Grab it for quick fake news erkennen spiel prototypes—great docs and UI, but 38 stars signal early maturity with no tests or included data. 0.800000011920929% credibility score raises flags on potential fake GitHub stars or history; fork and verify before production.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.