We agree - as independent of Twitter we have a considerable amount of freedom in how we build this. However Twitter can and should be doing much more. For example with a model they can start placing captchas before Tweets.
In addition to building the model we went about trying build our own bots. To do this we went on forums and contacted individuals selling "aged" accounts. It turns out its as simple as sending $4 over paypal to get a compromised account. These are accounts with histories, real followers, and real people behind them.
We bought 11 of these and were able to automate them within the hour of purchasing them. They also started receiving replies to their retweets and content almost immediately from all over twitter.
The ease of setting up these compromised accounts as bots was also incredibly worrisome. We've found high confidence heuristics to determine that an account has been compromised. If we can - Twitter should be able to as well.
We're ultimately a bit confused over Twitter's inactivity here. We also haven't heard anything from the company.
Here's our analysis if you want to read more.
analysis: https://medium.com/@robhat/an-analysis-of-propaganda-bots-on...
I think the "won't" may be accurate as if Twitter did it and chose not to act that would look terrible. And the scope of the bot problem may make their user base look a lot less attractive if they admitted it.
Granted everyone suspects, but there may be a valid reason they don't want to "know" at Twitter.