Past Articles by This Author:
BlackBerry to Launch BBM Messenger for iOS and Android this SummerApple vs. Samsung Update: Apple Adds Galaxy S4 to Massive LawsuitCondoleezza Rice, Walter Isaacson, Jim Collins to Headline ExactTarget Connections Sept. 17-19ChannelAdvisor and Google Host Webinar to Share Tips for Success with Enhanced CampaignsLeaf Unveils Second Generation of its Built-for-Business TabletBlackBerry Unveils Version 10.1 Now Available for Download for Enterprise UsersBlackBerry Announces Q5 a 'Youthful and Fun Smartphone' BlackBerry to Webcast Keynote and Alicia Keys Performance from OrlandoMcAfee and Intel Deliver New Model for Consumer Security - LiveSafeLeaf Unveils New POS Android Tablet
Twitter's Engineering blog has just released details on a new human computation engine that's now in play on the popular micro-blogging site.
"So an event happens, people instantly come to Twitter to search for the event, and 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.
How do we do this? We've built a real-time human computation engine to help us identify search queries as soon as they're trending, send these queries to real humans to be judged, and then incorporate the human annotations into our back-end models.
Before we delve into the details, here's an overview of how the system works.
- First, we monitor for which search queries are currently popular.
Behind the scenes: we run a Storm topology that tracks statistics on search queries.
For example, the query [Big Bird] may suddenly see a spike in searches from the US.
- 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.
Behind the scenes: when the Storm topology detects that a query has reached sufficient popularity, it connects to a Thrift API that dispatches the query to Amazon's Mechanical Turk service, and then polls Mechanical Turk for a response.
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 (e.g., whether there are likely to be interesting pictures of the query, or whether the query is about a person or an event) that helps us serve relevant Tweets and ads.
- Finally, after a response from an evaluator is received, we push the information to our backend systems, so that the next time a user searches for a query, our machine learning models will make use of the additional information. For example, suppose our evaluators tell us that [Big Bird] is related to politics; the next time someone performs this search, we know to surface ads by @barackobama or @mittromney, not ads about Dora the Explorer."
Click here for the full details.
More Articles by This Author...