How AI Is Used in Search Engines to Rank Search Results and Fight Spam
Artificial intelligence is a key technology used by search engines like Google to produce relevant results for users.
AI determines what content should be displayed and in what order. It also filters out low quality content and spam from search engine results pages (SERPs).
For any marketer looking to rank in SERPs, it's important to know the ins and outs of AI and search results.
Christi Olson (@ChristiJOlson) at Microsoft has you covered.
In her course for AI Academy for Marketers, AI and SPAM-a-lot: How Deep Learning Is Used to Create the Search Algorithms and Fights SPAM in Search Engines, she breaks down what you need to know.
The Search Engine Results Page
When you hear of the term “search engine," you may think of Google or Bing.
However, most people don’t think about the many components that go into each search engine.
Understanding these components is the first step to peeking behind the curtain of how search engines work. Some of the basic components include:
- Search Box: This may be the most common interface you have with any search engine: the box where you type in the question you want answered.
- Recommendations: The search engine is able to offer other suggestions in relation to past searches made on this topic.
- Organic Results: These are the results that appear based on their authority and ranking. This is different from paid advertisements, which only appear on a page because the company paid for them to be there.
- Map Results: A map may appear and show you the different locations within your radius.
These are just a few examples of what a search engine is composed of and the benefits it delivers to the consumer. However, there are plenty of parts that most users cannot see. Search algorithms are included in this list.
The History of Search Algorithms
The first form of a search algorithm was called “frequency." If you were to search for information on a certain word or topic, then you would search for the piece of content that contained that word most frequently.
To calculate the frequency of your keyword on a page, search engines would divide the number of times keywords appeared on a page by the total number of words on the page.
Today, the process for search algorithms is more complex—and effective.
Location of keywords in articles is important. A keyword located in a title rather than mentioned once in a paragraph is going to receive more attention from search engines. This is because a title is deemed of higher importance.
There is now a complex process behind modern search that involves comparing vectors, which determine search intent, to queries, or the question being asked by the user.
The closer the vector and query are, the closer their intent is. This is what deems certain articles to be more relevant than others.
A common method used by spammers in the past was to scrape quality content created by a company and replace all the keywords to something similar. For example, if an article discussed “10 Best Places for Kids in NYC," the spammer may rewrite that phrase as “10 Best Places for Children in NYC." Other spammers would simply scrape an article and re-order the content.
More complex spammers today try to hack into search algorithms themselves. The good news is that deep learning (a form of AI) helps us detect these more advanced spam techniques.
Watch the course listed below to learn more in detail what you can do to fight spam.
Want To Learn More About What AI Can Do For You?
These insights came from AI and SPAM-a-lot: How Deep Learning Is Used to Create the Search Algorithms and Fights SPAM in Search Engines, an AI Academy for Marketers course presented by Christi Olson (@ChristiJOlson) of Microsoft.
AI Academy for Marketers is our members-only online education platform and community. The Academy features dozens of on-demand courses and certifications taught by leading AI and marketing experts.
The 25+ courses available in AI Academy are complemented by additional exclusive content, including:
- Live monthly Ask Me Anything sessions with instructors.
- The Answering AI series of quick-take videos that provides simple answers to common AI questions.
- Keynote presentations from the Marketing AI Conference (MAICON).
- AI Tech Showcase product demos from leading AI-powered vendors.