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
-
Twitter Gets Social With Viacom June 19, 5:21 p.m.
Twitter took another step Wednesday toward supporting television. The social-media company signed a partnership with Viacom ... -
Digital, Alternative Media Revs Forecast To Hit $436B By 2017 June 19, 3:01 p.m.
Various types of mobile marketing and advertising accounted for nine of the top 10 fastest-growing digital ... -
Acquisitions Flourish, Google To Seek Equity Firm To Further Deals June 19, 1:24 p.m.
Google is considering alliances with private-equity firms to help structure acquisition deals, but the tech company ... -
Millennial Expands Video Ad Options June 19, 11:44 a.m.
Mobile ad network Millennial Media is stepping up its video ad offerings with the launch of ... -
CIMM Issues Request For Data, Cross-Platform Metrics June 19, 9:29 a.m.
The Coalition for Innovative Media Measurement (CIMM) said it has issued a request for proposals involving ... -
Heads Or Tails: Facebook Grows A Long One, Surpasses 1 Million Advertisers June 19, 7:48 a.m.
Facebook has reached an important ad industry milestone, becoming one of the few mega platforms to ... -
Consumer Action: Most Web Users Want Control Over Tracking June 18, 8:20 p.m.
Most Web users have expectations about privacy that appear to be at odds with current practices ... -
Affiliate Channels Attract Global Buying, Tailored Marketing Programs June 18, 5:54 p.m.
The Internet continues to make the world smaller for affiliate marketers, but there are physical challenges ... -
Motorola Hires Digitas For Global Media Account June 18, 5:43 p.m.
Google-owned Motorola has appointed Publicis Groupe’s Digitas to handle global media duties, according to sources. Those ... -
Microsoft Rolls Out Ad Pano, Mobile Ad Format June 18, 3:03 p.m.
With the help of the broader ad industry, Microsoft this week is rolling out a mobile ...
Be the first to comment on "Twitter Combines Human Factor, New Tech To Refine Real-Time Search"
Leave a Comment