{"id":10064,"date":"2019-01-23T17:00:00","date_gmt":"2019-01-23T16:00:00","guid":{"rendered":"https:\/\/wordlift.io\/blog\/en\/?p=10064"},"modified":"2021-12-23T10:02:19","modified_gmt":"2021-12-23T09:02:19","slug":"machine-learning-for-seo","status":"publish","type":"post","link":"https:\/\/wordlift.io\/blog\/en\/machine-learning-for-seo\/","title":{"rendered":"Machine Learning For Seo: How To Improve Seo With AI"},"content":{"rendered":"\r\n

Does SEO use machine learning?<\/strong><\/h2>\r\n\r\n\r\n\r\n

In this post, I\u2019ll walk through the analysis of Google Search Console data combined with a machine learning clustering technique to <\/span>provide an indication of what pages<\/a> can be optimized to improve the organic traffic <\/a><\/b>of a company website<\/a>. I will also highlight the lessons I learned while using machine learning for an SEO task.<\/span><\/p>\r\n\r\n\r\n\r\n

Interestingly, website owners when I propose to use their data are usually very relieved that AI can take care of the mundane, repetitive SEO work like analyzing GSC data; this allows the clients of our <\/span>SEO management service<\/span><\/a> and our own team, to focus on more complex, value-adding work such as content writing, content enrichment, and monetization.<\/span><\/p>\r\n\r\n\r\n\r\n

How does machine learning work?<\/strong><\/span><\/h2>\r\n\r\n\r\n\r\n

This experiment is designed for anyone: no specific coding skill is required. A good grip on Google Sheets is more than enough to get you started in the data mining of your website\u2019s GSC data.<\/span><\/p>\r\n\r\n\r\n\r\n

We will use <\/span>Orange<\/b><\/span>, an open-source tool<\/span><\/i> built on top of Python, for data mining and analysis that uses <\/span>a visual programming front-end<\/b><\/span> (a graphical user interface that lets you do what a developer would do using a Jupyter notebook environment and Python, yay!).<\/p>\r\n\r\n\r\n\r\n

You can install Orange from Anaconda, a popular Python data science platform, or simply <\/span>download it and install it from their website<\/span><\/a>. We will also use data from a web crawler to extract information about the length of the title and the length of the meta description. This can be done using a WooRank account<\/a><\/strong>, Sitebulb<\/a> or any other web crawler of your choosing.  <\/span><\/p>\r\n\r\n\r\n\r\n

What is machine learning in SEO?<\/strong><\/span><\/h2>\r\n\r\n\r\n\r\n

Dealing with machine learning is indeed <\/span>a paradigm shift<\/span><\/i>. The basic idea is that we provide highly curated data to a machine and the machine will learn from this data, it will program itself and it will help us in the analysis by either grouping data points, making predictions or extracting relevant patterns from our dataset. <\/span>Choosing the data points and curating the dataset, in machine learning, is as strategic as writing the computer program in traditional computer science<\/b>. By deciding the type of data you will feed the machine you are transferring the knowledge required to train the machine. To do so, you need the so-called domain experts and when I started with this experiment I came across a tweet from Bill Slawski that indicated to me the importance of <\/span>comparing search impressions to clicks<\/b> on a page as the most valuable piece of data from the Google Search Console.<\/span><\/p>\r\n\r\n\r\n\r\n

<\/p>\r\n\r\n\r\n\r\n

A3 One of my favorite GSC Data points is comparing search impressions to click on a page, if they vary widely is a sign that rewriting titles or snippets would be a good idea – less of a sign of success of an ongoing campaign, but helpful to know about. #SEOChat<\/a><\/p>\u2014 Bill Slawski \u2693 (@bill_slawski) January 10, 2019<\/a><\/blockquote>