Twitter’s use of actual humans to make sense of its search results, points to the mundane reality that even with machine learning and lots of data, sometimes humans are the best source for insights.
Check out twitter’s post http://tinyurl.com/ar6dqyw
As soon as twitter discovers a new popular search query, they send it to human evaluators on Amazon’s Mechanical Turk service, who are asked a variety of questions about the query. The feedback from humans is then fed to the machine learning models that will make use of the additional information