Twitter Combines Human Factor, New Tech To Refine Real-Time Search
Twitter has integrated human intelligence to help evaluate search results, such as the meaning of trending hashtags and why specific topics relate to intent.
The real-time computation system supports search to help identify keywords at the moment they begin to trend -- something missing in the world of real-time results. Making this possible are several technologies, such as Scalding, Storm and FlockDB.
Human intervention, coupled with theese technologies, will help the company understand what people think rather than type. Machines will interpret intent through words and timing, and search marketers will work with artificial intelligence.
The process begins with a technology called Storm, which processes streams of new data and updates in real-time, rather than in batches for update at a later time.
Behind the scenes, the Storm topology detects when queries reach sufficient popularity, while automating a query to a Thrift API that dispatches it to Amazon's Mechanical Turk service, and then polls the platform for a response. The queries get passed to human evaluators to analyze the outcome.
They push the information to Twitter's back-end systems, so that the next time a user searches for a query, the company's machine-learning models will make use of the additional information.
Twitter engineers Edwin Chen and Alpa Jain say the company relies on crowdsourcing, described as a "small custom pool of Mechanical Turk judges to ensure high quality."
Twitter has considered other possibilities for crowdsourcing, such as testing the use of in-house judges, standard worker filters that Amazon provides, and going through an outside company like Crowdflower. The two explain how Mechanical Turk judges work best.
Recent Online Media Daily Articles
-
Entertainment, Travel Bet On Mobile Banners May 22, 4:16 p.m.
Banner ads have long been the whipping boy of online advertising, and the same is now ... -
Marketers Should Tailor Specific Pitches To Tablet, Smartphone May 22, 2:51 p.m.
Don’t lump tablets in with mobile. That’s the takeaway of a new Forrester study looking at ... -
Good TV Content Trumps On, Whether Trad TV Or Streaming May 22, 2:42 p.m.
While consumers continue to perceive TV programming as superior in quality to that of online fare, ... -
Google Releases Self-Serve Display Benchmark Tool May 22, 2:02 p.m.
Understanding how a brand's online campaign competes with competitors requires trending benchmark data like engagement rates ... -
Twitter Brings Lead Generation To Tweets May 22, 1:14 p.m.
Twitter began testing a lead generation tool Wednesday in its tweet stream that resembles a cross ... -
DigitasLBi, Razorfish Tap Execs For Global Ops May 22, 11:26 a.m.
Publicis Groupe digital agencies DigitasLBi and Razorfish have installed new executives to run their respective international ... -
More Consumers Turn To Mobile To Research, Book Travel May 22, 8:53 a.m.
More than half of consumers used a mobile device to book travel in the last 90 ... -
Showrooming Overhyped, Mobile Key To Shopping Purchases May 22, 8:53 a.m.
Given consumers' mobile in-store shopping trends, some consider the showrooming hoopla overblown. The research process still ... -
Shopping App Swirl Adds In-Store Capability May 22, 8:53 a.m.
Swirl entered the mobile shopping fray last year with an iPhone app allowing users to learn ... -
Tablets Gain Popularity With Shoppers May 22, 8:53 a.m.
Internet-connected devices are exploding in the United States. There are 31.8 million Internet-accessible tablets, according to ...
Be the first to comment on "Twitter Combines Human Factor, New Tech To Refine Real-Time Search"
Leave a Comment