Building an Environmental Sustainability Dictionary for the IT Industry

Abstract

Content analysis is a commonly utilized methodology in corporate sustainability research. However, because most corporate sustainability research using content analysis is based on human coding, the research capability and the scope of the research design has limitations. The relatively recent text mining technique addresses some of the limitations of manual content analysis but its usage is often dependent upon the development of a domain specific dictionary. This paper develops an environmental sustainability dictionary in the context of corporate sustainability reports for the IT industry. In support of building said dictionary, we develop a standardized dictionary building process model that can be applied across many domains.

“Sustainability-contents SEO”: a semantic algorithm to improve the quality rating of sustainability web contents

“…In this case, it is a database populated by terms and phrases belonging to the language of sustainability, organized according to a taxonomic structure that groups them by sustainability themes. The systematization of the terminology of the sustainability language envisaged the establishment of a controlled vocabulary, following the procedure outlined by Deng et al (2017). The corpus of terms of the vocabulary has been elaborated starting from three dictionaries or encyclopaedias already published on the subject (Beck, 2014; Idowu et al , 2015; Robertson, 2017).…”

Analyzing Trends and Topics in Internet Governance and Cybersecurity Debates Found in Twelve Years of IGF Transcripts

“…Categorization modeling (known more generically as dictionary development), is an explicitly deductive technique [23] [24]. Essentially, what dictionary development requires is to develop a semantic structure that represents the concept one wants to explore within the dataset.…”

“…In contrast, deductive techniques are confirmatory, and allow us to ask specific research questions of the data and to even test hypotheses. We can build, adopt, or adapt dictionaries or categorization models to help us explore specific topics in the dataset, to determine the degree of their presence or absence [23] [24]. Specific variants of these models allow us to conduct sentiment analysis, to characterize positive and negative sentiment or polarity within the dataset [25].…”

Text Mining Narrative Survey Responses to Develop Engagement Scale Items

“…Although important in a more exhaustive review, lower frequency words do not help as much to identify a small number of broad themes in a large data set. This five-case cutoff was arbitrarily chosen, but necessary to impose practical constraints on the process [21]. The analysis then focused on 4,153 unique words and 20,478 unique phrases.…”