Swan AI

Using AI to counter misinformation and fake news faced by oridinary people.

Sultan Abdul Kader Syed Mohamed
TU Delft
MSc Electrical Engineering

Over het initiatief / About the initiative

Swan AI

In welke fase zit jouw initiatief? / In what stage is your initiative?


Heb je jouw initiatief al gevalideerd? / Did you validate your initiative?

Not yet, planning to do it soon

Meer informatie over jouw initiatief / More info about your initiative

In today’s fast-paced, data-driven world, news and breakthroughs from around the globe are made available to everyone in seconds. Beyond news websites and apps, the other fragmented sources include the social media platforms such as Youtube, Whatsapp, Tiktok, Facebook and X which continuously shape public opinion and decision-making. As a result, new generation of news content creators are arising and presenting the news from their own biased perspectives. Additionally, some malicious entities use social media to push propanganda and out-of-context information.

The prevalence of such misinformation and emotionally charged content has led to widespread manipulation of narratives, eroding trust in the media. Even established news outlets struggle to verify information quickly while competing to be the first to publish.

To increase the trustability in news and deepen audience relationship, we propose Swan AI. Swan AI addresses this challenge by using verified factual data to assess the accuracy of news reports, providing a credibility score with supporting evidence. Swan AI eliminates emotional biases in articles, looks at statistics, surveys (including their credibility), and other objective factors to ensure that news is unbiased and grounded in actual data.

Wat is er anders/nieuw aan jouw idee/oplossing t.o.v. bestaande oplossingen? / What is different/new about your idea/solution compared to existing solutions??

  1. Swan AI removes both intentional and unintentional biases (caused due to human errors) in news articles.
  2. It helps in properly segregating the facts from opinions inside a news article.
  3. By using AI, our model is scalable and can be added on top of the individual’s preferred source of news.
  4. The existing solutions use humans to validate the news which is very cumbersome, expensive and time consuming. This can be solved with Swan AI.
  5. This additionally gives more credibility and reliability to news outlets which operate more ethically, instead of supporting clickbait content.

Wat zijn jouw volgende stappen om het verder te ontwikkelen? / What are your next steps to develop the initiative?

  • We are working on the market research.
  • Simultaneously we are developing an AI model for testing the idea.
  • A roadmap to test the idea and validate is already in place.
  • We are looking for one or two enthusiastic people, to help with the idea.
  • We are in contact with a AI professor in TU Deflt, to help with develop.

Wat heb je nodig om (nog meer) impact te maken met dit initiatief? / What do you need to make (more) impact with this initiative?

  1. We are looking for a mentor for how to develop this as a business model.
  2. We are getting to know fact-checking, and journalism methods to implement in our model.
  3. A partnering journalism outlet will help a lot with refining the model.