Giter Site home page Giter Site logo

hackitect / see-the-light Goto Github PK

View Code? Open in Web Editor NEW

This project forked from andelahacks/see-the-light

0.0 2.0 0.0 833 KB

Smart App to flag fake news articles and rank websites reputation and ranking

License: MIT License

Python 28.66% Java 71.34%

see-the-light's Introduction

TEAM SeeTheLight(STL) - ANDELA NEWS HACKATHON

Badges

Maintainability

Contributors

Simon Injiri
Brian Wandera
Charles Njenga
Catherine Wanjiru

The Project consists of a machine learning model that is the backend of our project. The ML model tests and trains it's data using the WebHouse Dataset which we implemented as an API used in the Android app and the front end web plugin.

The output displays a percentage confidence of real or fake, similarity of text to title, and polarity of the text.

IP address/Domain reputation checker

The STL API queries the Tallos Intelligence Resources and the Public API for Apility.io for much of the analytics in regards to IP and Domain Checker. These three checks -IP address blacklist, Domain blacklist and IP address historical blacklist- are summarized and returned as a global score for the IP address.

This API call also returns detailed information about the IP address from different sources:

  • when the domain was registered and the registrar
  • IP Geolocation
  • AS information
  • WHOIS informaton
  • Blacklists where the IP address was found (if any).
  • Blacklists where the Hostname was found (if any).

Android Application

The project does not require a user to download any machine learning library but only download the apk of the application from this site https://drive.google.com/file/d/1nAvX97uhTnjMkT_q4RkZ4-tbi_gMBIsv/view?usp=sharing. After installing the android application, the user will be able to paste the urls into the application and it is parsed in the API of the machine Learning model

alt text

Web Plugin

It works on the same procedure as the android app but by having a Web Extension being installed in the browser which extacts the webpage being browsed and parses the data using the Machine Learning model API.

Machine Learning Model

The See The Light API uses part of the Machine Learning Model developed by @bmbejcek. The See The Light app goes ahead and adds dns credibility assessment to check on the source of the story. If such a site is associated with fake news, then it reduces the credibility of such a site.

API Endpoints

The API endpoint to check the authenticity of a news article is: Click Here To View A Demo of the API

see-the-light's People

Contributors

wandesky avatar hackitect avatar wanjirucate avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.