Intelligent Corporate Sustainability report scoring solution using machine learning approach to text categorization

Abstract

Development of an intelligent software system to analyze and score Corporate Sustainability reports within the Global Reporting Initiative (GRI) framework has been well foreseen and in a high demand since the latest framework's publication in 2000's. As the number of reporting organizations and published reports is increasing exponentially, development of a software system to automate the daunting manual scoring process seems even more vital. We describe our preliminary efforts and the related results of our efforts in building such software through application of machine learning approach to text classification. Conduction of earlier training on thousands of sample documents to construct machine learning based classifiers inductively is our primary approach to solving this problem.