Hacker News Reader

I would read this post if you wrote it... because I don't know what word2vec & doc2vec are and why they are useful.

If you write the post maybe someone will be inspired to build a tool for journalists using these algos.

None of the journalists I have met or worked with in six years in publishing and investigative due diligence know about the tools you are proposing. I recognize regex, because of a problem I needed to solve (that later became two problems), but I would love to learn more about the others. If you would consider writing that up, I would happily edit it for you.

That's an interesting question - if you read the stories of how Edward Snowden's story came to light, you'll find that his main issue with Glenn Greenwald was to get the guy to use technology properly.

Hopefully out of the many tech heads who read HN, one will have the same thought as you and build the tool.