Twitter Search With A Dash Of Human

Jan 10, 2013 • 8:26 am | comments (0) by twitter Google+ | Filed Under Social Search Engines & Optimization
 

Twitter LogoTwitter announced on their engineering blog explained how they handle search queries that are related to events and things spiking at the time. In short, they supplement their algorithms with human editors to improve the search quality.

Twitter explained it as follows:

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.

Here is the overview of how it works, but Twitter in the blog post gets a lot more detailed:

(1) 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.

(2) 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.

(3) 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.

That is a glimpse into how Twitter Search works.

Forum discussion at WebmasterWorld.

Previous story: Googler Complains: Google Maps On Android A Drain
 

Comments:

No comments.

blog comments powered by Disqus