NotJustSerafim
I sent email today. Let's keep in touch
About fact-checking. I think this feature contains two big parts: 1) extract a fact from the text 2) to check a fact
For 1s task on the basic level and numeric data, it seems not so difficult with NLP (just tried to create a tree and it looks pretty simple: https://nbviewer.jupyter.org/github/SerafimPikalov/Sandbox/b...)
For 2nd task probably needs to create some kind of "fact-tree" (something like Word population>USA population>target audience for service potential audience...)
Just yesterday I had a talk with my friend with the PR industry. We have been discussing how to select the best information sources and became to the idea that the future will be some kind of rating system based on pair experts-field of knowledge. After that, I start to think about creating some kind of automatic system for fact-checking facts in articles at least numerous ones (like based on world population and companies valuation and other public data). Do you have anything like this in your backlog?