Topic modelling is nowadays one of the most popular techniques used to extract knowledge from texts. There are several families of methods related to this problem, among them 1) Factorial methods, 2) Probabilistic methods and 3) Natural Language Processing methods. In this paper a common conceptual framework is provided for Factorial and probabilistic methods by identifying common elements and describing them with common and homogeneous notation and 7 different methods are described accordingly. Under a common notation it is easy to make a comparative analysis and see how flexible or more or less realistic assumptions are made by the different methods. This is the first step to a wider analysis where all families can be related to this common conceptual framework and to go in depth in the understanding of stengths and weakenesses of each method and ellaboration of general guidelines to provide application criteria. The paper ends with a discussion comparing the presented methods and future research lines.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com