termdocument

Termdocument is a concept used in information retrieval and text analytics to describe the association between a term and a specific document. In practice, a termdocument refers to a record that captures the occurrence or presence of a term within a document and it forms part of larger data structures such as a term-document matrix or an inverted index.

A typical termdocument entry includes fields such as the term itself, the document identifier, and a measure of the term’s occurrence. Common variants include binary presence (the term occurs or does not occur in the document), term frequency (the number of times the term appears), and positional information (the locations of the term within the document). When aggregated across a corpus, termdocuments support weighting schemes like TF-IDF, which balance term frequency with how broadly a term appears across documents.

Inverted indexes use a collection of termdocuments to map each term to the documents in which it appears, enabling efficient query processing. Termdocuments also underpin a document-term matrix, where rows represent documents and columns represent terms, with matrix entries reflecting term frequencies or weighted scores.

Applications include search engines, document clustering, topic modeling, and keyword extraction. A well-designed termdocument representation supports fast retrieval, accurate ranking, and scalable analysis of large text corpora. In practice, systems may store termdocuments in compressed or sparse formats to handle the vast number of possible term-document pairs in real-world datasets.

See also: term frequency, inverse document frequency, TF-IDF, inverted index, document-term matrix.