Better understand user intent Better assess the quality of content We also know that Google (and other engines) also want to leverage user satisfaction/user engagement data. While it's less clear what signals they'll be entering, it seems likely that's another place where machine learning is playing a role. Today I'm going to explore the state of the state when it comes to content quality and how I think machine learning is likely to drive the evolution of that. Content Quality Improvement Case Studies A lot of the sites we see continue to underinvest in adding content to their pages.
This is very common with e-commerce sites. Too many of them create their pages, add the products and product descriptions, and then think they're done. It is a mistake. For example, adding product -specific unique user reviews on the page is very effective. At Stone jewelry retouching service Temple, we worked on a site where adding user reviews led to a 45% increase in traffic on the pages included in the test. We also did a test where we took existing text on category pages that were originally designed as “SEO text” and replaced it. The so-called
SEO text was not written with users in mind and therefore added little value to the page. We replaced the SEO text with a true mini-guide specific to the categories the content resided on. We saw a 68% gain in traffic to these pages. We also had control pages that we made no changes to, and traffic to these dropped by 11%, so the net gain was just under 80%: impact of new content Note that our text was handcrafted and tuned for the explicit purpose of adding value to the tested pages. So it wasn't cheap or easy to implement, but it was still quite profitable, considering we did it on the main category pages of the site.