What is TF-IDF?
TF–IDF, or Term Frequency – Inverse Document Frequency, is a statistical technique for detecting the most important words in a document.
TF-IDF measures how frequently a word appears in an article. However, it adjusts the measurement for commonly used words as they are expected to occur more often. That way, these commonly used words cannot skew the measurement.
Many search engines use TF–IDF as part of their algorithms to match search queries to relevant content.