Algorithm of similarity (themes) of news

I want to determine the similarity of the content of the two news, similar to Google news, but different in the sense that I want to determine which main topics then determine which topics are related.

So, if the article was about Saddam Hussein, then the algorithm could recommend something about the business deals of Donald Rumsfeld in Iraq.

If you can just drop keywords, such as the k-nearest neighbors, and a short explanation of why they work (if possible), I will do the rest of the analysis and set up the algorithm. Just look for a place to start, as I know that someone there must have tried something like this before.

+3
source share
2 answers

:

  • (, , , ,...).
  • .
  • ( - ) .
  • .

, , , , .

, , , Microsoft . .

:

, , - .

, ( ).

, ( , ). (Microsoft , ).

, , , " ", ( , ).

"" (, ). , , .

+5

- .

- . ​​, , , , , , , , . , .

, . , .

, , , . , , , , ... .

- .

0

Source: https://habr.com/ru/post/1706161/


All Articles