Who is horse_js?

In case you didn't notice, this is clever advertising for Microsoft Azure. Both authors work for Microsoft. I could count 3 mentions of Azure, two direct links to Azure products, 1 quote from a Microsoft researcher, 1 quote from a Microsoft dev advocate and 1 embedded Bing maps. You've just been played by Microsoft marketing. Also, Tom Dale works for Microsoft himself so it's just one big family story.

This wasn't very rigorous at all, but it was a moderately fun read because it really made it clear how "large amounts of data" with some simple visualization can help people make some mostly-educated guesses.

I was most surprised at them glossing over the activity patterns with guesses based on their assumption of the target's sleeping patterns -- their guess of a time zone would have been stymied by someone who liked to sleep early/late or had an unusual work schedule, but there was no mention of that or their reasoning.

That all made sense given patrickaljord's comment about it all being one big Microsoft ad, though.

Bug report: time series analysis chart fails to display properly on Firefox, all points stay on x=0, I see "Unexpected value NaN parsing cx attribute" x250 in the console. Works fine on Chrome.

The article was quite enjoyable to read though full of MS marketing.

When saw the part with Azure Cognitive Services Text Analytics - I burst out laughing. Earlier, they quoted: Half of the time when companies say they need "AI" what they really need is a SELECT clause with GROUP BY.

Their motivation of using AI is even below that threshold.

Now awaiting some horse_js comment about this absurdity.

I'm clearly a terrible person, but I read the reveal and immediately thought "But X isn't funny enough to be horse_js!"

I was scrolling through the whole article raging for an ethics paragraph, but I guess they handled that pretty well.

With a nifty and I think necessary touch of themselves still being in the dark; I very much doubt that the data they gathered can really reveal the author's identity, and the result they arrived on (Tom Dale) seems to largely originate from the "quotes one person far more than others" metric.

You could almost consider it an anti-metric: which intently pseudonymous author would dare to retweet their own nym? However, to counter this analysis you'd have to blend in with the average Twitter user in your niche, so it then comes down to a psychological game of "what would horse_js do?".

Just use elasticsearch/kibana and you will save yourselves from lots of Azure costs. Find keywords and group by device and location. Simple as that.

> @horse_js lives in either the Central or Eastern time zone. Their activity dwindles sharply in the evening and disapears between ~11 PM - 12 AM CST and reappears at ~8 AM - 9 AM CST because they are likely asleep.

As someone commenting at 4 AM, this might not be a great assumption to make ;)

Very fun read, it contains just the right amount of detail to stay entertaining without getting bogged down in minutiae.

> "But I already know who @horse_js is, and it's not [...]!"

Perhaps. The data here is not 100% conclusive. There are some critical assumptions holding up our conclusion and [...] has never confirmed (or denied) our findings.

Perhaps the horse lives to tweet another day...

Ironically this highlights one of the main problems with how machine learning is used.

On a very high level, I think you can sum up machine learning algorithms as finding pattern in enormous heaps of noisy data ("training") then trying to apply the discovered pattern to novel data and using the result to guess the answer to a question you posed ("predicting").

The keyword being guess here. Unlike algorithms not based on learning, there is no guarantee that the answer is correct, because you usually don't know if the training data you supplied was sufficient or if the learned patterns were the ones you need. If you knew, you could just hard code the patterns directly and get rid of the whole learning overhead altogether.

Researchers know and communicate this. However, in the press, "AI" seems to be seen as almost the exact opposite: Not only can those fantasy AI systems answer questions about fuzzy human concepts with the precision of a computer, their answers are even better than the human ones - which is why the things we need to worry about are ethics discussions and humanity becoming obsolete...

This could be funny if it were just restricted to science fiction and public discussion, but it becomes problematic when "AI" systems are used to make life-changing descisions like setting insurance premiums or declaring persons suspicious to law enforcement.

> The API is rate limited, so we created a set of Node.js Azure Functions that ran on a timers. These functions would request as many tweets as they could before they were rate limited, wait for the timeout interval specified by the API docs, then resume processing where they left off.

How does this work? You pay for your function's run time in serverless so you wouldn't want to just have the function sleep for x minutes or however long it gets rate limited surely. I can see a way to do it using a service bus queue (push the message with a delay of x minutes, have the function set up to run on messages on that queue) but they specifically said timers. Does Azure let you programatically set the timer for a function from inside that function (eg. "Run me again in 3 minutes")?

Its interesting but also worrying. This is pretty much doxxing under the guise of intellectual curiosity.

If the article explained why they wanted to identify this account then fair enough. However you are going to end up in an ethical slippery slope were it will be used to doxx people who are controversial, troll, political dissidents and whistle blowers.

This is marketing. Someone should flag it.

I am so tired of Microsoft meddling in the developer space. I wish they just crawled away and made themselves irrelevant. If not for the money and how they shove they products in people's throats nobody would consider even using them. Internet? They had to taint it with IE6. Operating systems? The dreadful Windows 10 malware OS. Then lure developers with their software, which if you have money then you can produce a ton of and just crush everything that is good in the IT.

Tweet from Tom Dale himself https://twitter.com/tomdale/status/1086675110801625089

> Finally. Some Machine Learning.

> We ran all of @horse_js tweets from the last 2 years through Azure Cognitive Services Text Analytics service. This service identifies keywords in phrases.

How was that necessary in comparison to a simple "split by whitespace, count occurences"? :P

cluster horse_js and Tom Dale's tweets in an embedding space and you can confirm your hypothesis.

So why was this a statistics problem?

That was a nice, fun read, and a simple way to show how sometimes, simple data analysis and common sense trumps everything else :)

Also, great website design. Simple and clean!

Neat concept, wonderful execution, and beautiful presentation. Now if only the entire web could follow suit.

Nice try, Angelina Fabbro

not knowing is half the fun.

lon ingram

This is journalism!

This is very bad. They spoiled it for everyone. That privacy disclaimer at the end is of no use really. Also Bing maps? Thats the first time I saw that.