Web Content Mining for Comparing Corporate and Third Party Online Reporting: A Case Study on Solid Waste Management

Abstract

This study investigates the coverage of solid waste management on 1142 websites maintained by companies, news media and non-governmental organizations to validate an automated approach to content and language analysis. First, a frequency analysis of waste management terms sheds light on the breadth and depth of their environmental discourses, revealing that corporate and media attention to waste management is small compared with that of non-governmental organizations. Second, an investigation of their attitudes toward waste management suggests that companies avoid negative information in environmental communication, unlike news media or non-governmental organizations. Ultimately, an automated tool for ontology building is employed to gain insights into companies' shared understanding of waste management. The ontology obtained indicates that companies conceptualize waste management as a business process rather than framing it from an ecological perspective, which is in line with findings from previous research.