Fake news identification
Request
Develop a model to assign a score to each piece of news on the Web, measuring the probability of it being a fake.
Approach
By training AI models with data from semantic analysis and technical page data, we created an engine that responds to URL analysis requests with a "Fake News Index”.
Result
70%+ of fake news identified, with less than 5% of legitimate news marked in the top 25% of higher scores.
Categories
Type
AI & Data Science
Need
Benefit
Business function
Industry
Business Model
Business Size
