Visualizing Term Eigenvector Prominence in a Corporate Social Responsibility Context
Abstract
In this study we develop a simplified technique for helping researchers and analysts visualize the alternative prominence of term eigenvectors obtained after exploring term associations (Term Clusters) while conducting Text Data Mining on a collection to Corporate Social Responsibility (CSR) reports. The collection analyzed is comprised of CSR reports produced by 7 US firms (Citi, Coca-Cola, Exxon-Mobil, General Motors, Intel, McDonald’s and Microsoft) in 2004, 2008 and 2012. The analysis is performed by year in order to discern how the prominence of term eigenvectors has evolved for each firm and for different CSR topics. Results indicate that term eigenvectors maintain their prominence when CSR topics are related to the core business of the firm in question.
The (A) Assignor declares that (s) text (s) concerned is (are) of his personal authorship, being responsible, therefore, for the originality of the (s) even (s) and gives the organizers, full rights to choice of publisher, publication means, means of reproduction, dissemination of media, drawing, shape, everything that is needed for that publication be effected.
PUBLISHER undertakes to ensure the editorial quality of the publication, ensuring that the concepts and the thought of (a) ASSIGNOR remain faithful to the original. This assignment will be valid throughout the period of legal protection WORK, may hold the PUBLISHER will be shown how many issues it deems appropriate.
All rights are reserved. Any reproduction, even if part of the publication should include the reference credit, according to the current copyright law of Brazil. Still, the article submission process, the author agrees to the terms of an exclusive statement, originality and agreement to the final version. It is justified in the field "; COMMENTS TO THE EDITOR" ;, when the participation of more than one author.
