Study finds Google search results are more relevant than ever

Machine learning and AI are helping Google deliver its most relevant results to date, a study found.

Google’s use of machine learning and artificial intelligence to better understand search intention and deliver the most relevant results is resulting in just that, according to new research from SEO and content performance platform Searchmetrics in its annual study of Google ranking factors.

According to Searchmetrics, not only are search results more relevant than ever, many simplistic techniques to artificially inflate page rank ‒ like collecting backlinks and increasing the number of times keywords are mentioned in text – are becoming less effective. Backlinks are also becoming less important because of the rise of mobile search queries because pages viewed on mobile devices are often liked or shared but seldom linked to, Searchmetrics added.

Searchmetrics analyzed the top 20 search results for 10,000 keywords on Google.com. The goal was to identify the key factors that high-ranking pages have in common.

“Google revealed last year that it is turning to sophisticated AI and machine learning techniques, such as its RankBrain system, to help it better understand the real intention behind the words that searchers enter in the search box and make its results more relevant,” said CTO Marcus Tober in a statement. “And with the help of user signals such as how often certain results are clicked and how long people spend there, the search engine gets a sense of how well searchers’ questions are answered, allowing it to continually refine and improve relevance.”

What’s more, Searchmetrics said the most relevant content ultimately depends on user intent.

“A searcher who types ‘Pesto Ingredients’ into the search box is most likely looking for a short list, for example. Someone who types ‘who won Super Bowl 50?’ wants a single piece of information, while a query like ‘halloween costume ideas’ is most likely wanting a series of images and a ‘how to tie a Windsor Knot’ query might be best served with video content,” Tober added. “Our research suggests Google is getting better at interpreting user intent to show the most relevant content.”

In addition, Searchmetrics found higher-ranking search results are significantly more relevant to a given query than those lower down.

Searchmetrics used what it called “Big Data techniques” to calculate a Content Relevance score, which it said is a new factor that assesses the semantic relationship between the words entered in search queries and the content shown in results and measures how closely they are related. And, Searchmetrics said, in general, the Content Relevance scores of results positioned near the top are higher, suggesting Google knows when content is more relevant and places it more prominently.

However, Searchmetrics noted this does not apply to results found in positions 1 and 2, which tend to be reserved for top brand websites, which is presumably because Google considers content from brands that are more recognizable and trusted will better serve searchers’ needs.

Searchmetrics also found word count is increasing on high-ranking pages while keyword mentions have dropped.

That’s because top-performing results are more detailed, more holistic and are better able to answer search queries, Searchmetrics said. But even as text grows longer, the number of keywords on higher ranked pages is not increasing. This is because Google is no longer just trying to reward pages that use more matching keywords – it is trying to interpret the search intention and boost the most relevant content, Searchmetrics said.

What’s more, Searchmetrics said data indicates Google is presenting precisely the right results to answer searchers’ queries as they visit those pages, take in what is there and leave without having to look elsewhere.

And, finally, Searchmetrics said Google is showing more longer URLs to answer queries rather than optimized short URLs.

In fact, the study found the URLs for pages that feature in the top 20 search results are about 15% longer on average than in 2015. Searchmetrics said this is likely because Google is better able to identify and display the precise pages that answer the search intention and these pages are more likely to have longer URLs because they possibly lie buried deeper within websites.

“Since Google is becoming much more sophisticated about how it interprets search intent and relevance, you also need to work harder and smarter at understanding and delivering on these areas in content you put on your websites,” Tober said. “You need to use data-driven insights to analyze exactly what searchers are looking for when they type specific queries in the search box and make sure your content answers all their questions clearly and comprehensively in the most straightforward way – and you need to do it better than your competitors.”

Get The Drum Newsletter

Build your marketing knowledge by choosing from daily news bulletins or a weekly special.