Term Frequency - Inverse Document Frequency (tf-idf)

Old technique (classical).

Term Frequency - Inverse Document Frequency (TF-IDF) is a widely used statistical method in natural language processing and information retrieval. It measures how important a term is within a document relative to a collection of documents (i.e., relative to a corpus).

$w_{ij}=t{f}_{ij}\log \frac{N}{d{f}_i}$

• $w_{ij}$ – weight (relevance) of term $i$ in document $j$
• $t{f}_{ij}$ – number of occurrences of term $i$ in document $j$
• $d{f}_i$ – number of documents containing term $I$
• $N$ – total number of documents

The relevance of a document is the sum of the $w_{i}j$ values over all $i$ that we care about.