Project Title: Know More
Introduction:
A famous personality tweets something, so it must be unbiased. Right?
Wrong. Don’t just believe anything you see.
We’ve all been in never-ending arguments with friends and family on critical issues like politics, international events or religion in the past. In recent years, however, we see a trend in people blindly trusting things they learnt from a video they saw last morning on WhatsApp or tweets by an influential personality. We all know what fake news or biased news can do to someone or something and how some people take advantage of such situations and spread fake news which might instigate people and form wrong opinions. This epidemic is especially prominent in people who grew up before the information age of computers and have never had to question the credibility of news sources in the past. Social media algorithms are built for engagement and likes, not perspective, and we aim to fix that with Know More..
Problems:
- The inability of people to create an internal filter against their own bias has caused the proliferation of false (or somewhat false) information to plague modern society and is slowly leading us to a world with only polarizing opinions.
- Today’s modern discovery algorithms trap us in our ‘filter bubbles’ by giving us content that agrees with our inherent biases regardless of whether these biases are grounded in reality.
Interface: Know More Bot is a Chrome extension (as of now) that has been developed for Twitter and integrated into the Twitter UI, the cause of a large number of celebrities and influential people from different profession use it as a tool to convey their thoughts and opinions. But we know that correct news is the one that is not biased or opinionated.
So what does it do?
Know More is a Machine Learning based web API that allows users to gain a broader perspective on news items and events and doesn’t keep them in their bubble and develop biased opinions. It provides with a global point of views by extracting news articles and Wikipedia using entity extraction and sentiment analysis.
- Know More Bot uses Natural Language Processing pipeline which performs entity and topic extraction from tweets to search for news articles from reliable sources and discover Wikipedia articles.
- After the entity extraction, we combine the information obtained with sentiment analysis signals for the tweet as well as the news articles to select articles which have a different perspective from the tweet.
Conceptual framework:
We will be making a Chrome extension which is integrated into the Twitter User Interface. When clicked it will extract the entities and provide news articles related to that topic and perform sentiment analysis of them which will be indicated using 3 colours (green – in favour, yellow – neutral and red – against along with Wikipedia article if available)
This is a highly modular project. It was built using the Agile method of Software Development Life Cycle.
Diagrams:
Flow Diagram
UI Mockup. Easy to use.
Working Model
UML diagram
Tools Used:
- Chrome Extension: To scrape tweets.
- Twitter API
- News API: To provide news articles.
- Google Natural Language API: For sentiment analysis and Natural Language processing.
- Python
- Flask
- JavaScript
- CSS
Application:
This project is for the betterment of the society. People nowadays spend more time on social media which is heavily biased. Know More Bot will provide them with various news articles and Wikipedia articles to broaden their perspective and understand the proper context and verify by themselves what is right and what is wrong.
Link to GitHub repository:
Server: Know More Server
Client: Know More Client
YouTube Video Link:
Research Work and Inspiration:
Team Members:
1. Sayak Kundu
2. Gulshan Mittal
3. Anurag Mehta
4. Parth Partani
Note: This project idea is contributed for ProGeek Cup 2.0- A project competition by GeeksforGeeks.