Using Word Association to Detect Multitopic Structures in Text Documents
André Klahold, Patrick Uhr, Fazel Ansari, Madjid Fathi · IEEE Intelligent Systems · 2013
A new method for detecting multitopic structures in text documents, called Associative Gravity, is based on a text-mining method entitled CIMAWA, which imitates the human ability of word association. Specifically, Associative Gravity utilizes word association to detect different topics in a text. The authors named it Associative Gravity because of its resemblance to the physical law of gravitation, that is, mass and attraction. The mass corresponds to the importance of words in a text and the attraction to the asymmetrical associative word space. The innovative characteristic of the described topic detection method is supplied with asymmetrical associative word space provided by CIMAWA. A comparative case study proves the capability of Associative Gravity to separate different topics at very high accuracy.