Text mining is a set of methods used to extract relevant information from texts in order to better understand textual data as well as for classification and categorization purposes.
There are several approaches in the field of text mining ranging from pLSA and LDA to tf-idf and lda2vec, which are also related to one another.
We created a visualization of the most prominent methods used in text mining today along with descriptions of the relations between them using InfraNodus. For instance, what’s the relation of pLSA to LDA or word2vec and lda2vec.
You can use this graph to better understand the various text mining approaches out there and to see how they can be used together. Simply click on the word-nodes to see the description of the relation between them. You can also click the “eye” button at the top right corner to Google more information.