-
Prompt to allow user to give their opinion on website
-
Reliability Rating (Factual)
-
Reliability Rating (Factual) Full information
-
Reliability Rating (False AI image)
-
Reliability Rating (False)
-
Reliability Rating (False) Full information
-
Landing page of the web-app
-
AI Fact checked analysis of the content
-
Exact errors and true facts
Project Story: Developing an AI to Detect False News
When we were given the challenge of selecting an AI solution from five key areas—medicine, crime, agriculture, learning, or the environment—we wanted to choose something that had a broad and immediate impact on society. After brainstorming and considering the real-world issues that technology could solve, we decided to focus on an AI that could detect false news and misinformation.
Why We Chose This Problem: In today’s digital world, false information spreads rapidly, influencing public opinions, shaping political outcomes, and even affecting people's health decisions. We saw how misinformation about vaccines, climate change, and even financial markets could cause real harm. By choosing to tackle this issue, we believed our AI could make a significant difference by helping people verify the accuracy of the information they consume.
Our Approach: To build an AI that detects false news, we researched how misinformation spreads and what makes a source reliable. We explored existing fact-checking methods and looked at AI models capable of analyzing text, comparing claims against verified sources, and detecting biased language.
Challenges We Faced: One of the biggest challenges was ensuring that our AI could differentiate between satire, opinion pieces, and actual misinformation. Another challenge was the risk of bias—since AI learns from existing data, it was crucial to train it on diverse sources to prevent it from favoring a particular viewpoint.
Impact & Future Potential: Our AI project demonstrated how technology can help combat misinformation. With further development, it could be integrated into social media platforms, news websites, or even browser extensions to help people verify information instantly. By empowering users with a tool that checks credibility, we hope to contribute to a more informed and responsible digital society.
Built With
- anthropic
- api
- axios
- cheerio
- claude
- css
- framer
- http
- next.js
- tailwind
- typescript
Log in or sign up for Devpost to join the conversation.