Google creates Knowledge Graph for better-targeted search results

Posted by Emma Woollacott

Google's introduced what it's calling the Knowledge Graph to search results, aiming to make them more context-relevant.

Starting today in the US - and soon in the rest of the world - the new feature is aimed at giving users more of what they're looking for. If, say, you search on 'Taj Mahal', it'll check whether you want the building in India or the restaurant down the road.

It'll also present users with a page of information about the subject of their search.

"How do we know which facts are most likely to be needed for each item? For that, we go back to our users and study in aggregate what they’ve been asking Google about each item," says senior VP for engineering Amit Signhal.

"For example, people are interested in knowing what books Charles Dickens wrote, whereas they’re less interested in what books Frank Lloyd Wright wrote, and more in what buildings he designed."

This means, says Singhal, that when a user searches on 'Tom Cruise', for example, the information shown answers their next query 37 percent of the time.

To do this, the company has mined public and private sources such as Freebase, Wikipedia and the CIA World Factbook to cover more than 500 million objects, as well as more than 3.5 billion facts about and relationships between these objects, making it something like the Wolfram Alpha search engine - or the Star trek computer, says Singhal.

The move comes just a week after Microsoft rolled out improvements to its own Bing search engine, highlighting results from social media. Google still leads the market, handling a little over two thirds of search queries, according to ComScore.