R tutorial: The TDM & DTM with text mining

With your clean corpus, you need to change the data structure for analysis. The foundation of bag of Words text mining is either the term document matrix or the document term matrix. The term document matrix has each corpus word represented as a row, with documents as columns. In this example, you simply use the term document matrix function on a corpus to create a tdm. The document term matrix is the transposition of the tdm, so each document is a row and each word is a column. Once again, the aptly named document term matrix function creates a matrix with documents as rows, shown here. In its simplest form, the matrices contain word frequencies. However, other frequency measures do exist. The QDAT package relies on a word frequency matrix. This course doesn't focus on the word frequency matrix, since it is less popular and can be made from a term document matrix.