Twitter reveals that people power lies behind analysing data in real time
Twitter has revealed that one of its key tools for analysing data in real time is people, not machines.
In a blog post, the engineering team explains that certain trending topics, such as the recent Mitt Romney inspired hashtag #bindersfullofwomen, prove difficult when building search or advertising tools.
The post explained that for computer algorithms, hashtags such as #bindersfullofwomen have “never before been seen, so it's impossible to know without very specific context what they mean.”
The post continued: “How would you know that #bindersfullofwomen refers to politics and not office accessories?
“Since these spikes in search queries are so short-lived, there’s only a small window of opportunity to learn what they mean.
“ … we need to teach our systems what these queries mean as quickly as we can — because in just a few hours, the search spike will be gone”.
As Twitter’s advertising business grows, understanding trending topics quickly is becoming more important as advertisers seek to target their messages to groups of members interested in particular areas, such as politics.
As such Twitter revealed it had hired its new “human computation engine” via Mechanical Turk, an Amazon service that links employers with home workers willing to do typically mundane tasks that computers remain incapable of, such as accurately transcribing speech.
It explained: “As soon as we discover a new popular search query, we send it to our human evaluators, who are asked a variety of questions about the query.
“For example: as soon as we notice "Big Bird" spiking, we may ask judges on Mechanical Turk to categorize the query, or provide other information that helps us serve relevant Tweets and ads.”
These evaluators, or “judges”, are found on Mechanical Turk, Amazon Web Services’ crowdsourcing service and, the Telegraph suggests, could be paid little as $3.73 p/h
The Telegraph's technology correspondent Christopher Williams writes that on Mechanical Turk the “task with the highest total pay on the service at time of writing was transcribing and tagging two and a quarter hours of video for $33.57.
“Professional transcribing firms estimate that an hour of video takes four hours to transcribe, so assuming home workers on Mechanical Turk could match that speed, they would be on a rate of $3.73 per hour.”