Abstract
Automatic text classification and topic extraction have received much attention from many fields, and various approaches for the problem have been proposed so far. In some of the proposed methods, a few ways of using Wikipedia data have been suggested and implemented. This paper presents a novel method to explore Wikipedia data to extract suitable topics from any given text document. The proposed method uses the network of Wikipedia articles and their categories to find most relevant Wikipedia categories for the given text. Finally, the method designates these most relevant categories as the topics of the document. An experimental result and the feasibility of the proposed method are illustrated.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
