In the science of information retrieval, tf–idf, short for term frequency – inverse document frequency, is a numerical statistic that is intended to reflect how important a word is to a document in a collection, according to Wikipedia, which also says that a survey conducted in 2015 showed that 83% of text-based recommender systems in digital libraries use tf–idf. In plainer English, tf–idf is a sophisticated way of showing the importance of a document to a particular search term by counting the occurrences of the term.
Twenty years ago, search engines worked like this. If we employed a search engine optimisation expert back then, they’d have been quite right to recommend that we stuffed our web pages full of the important search terms, many times over. But the search engines’ need to address a more commercial world meant that more sophisticated processes were developed, and nobody today would recommend ‘keyword stuffing’.
However, I have seen tf–idf discussed as an SEO technique in recent years, perhaps because it sounds technical. It does have its place, but not in SEO. Google in particular has little interest in how often terms appear in a document, and thousands of websites have been penalised for ‘keyword stuffing’ despite having had no intention of bending the rules. More than ever, we’ll give ourselves the best start in SEO by writing in natural language for our human readers.