A Text-Mining Approach to the Evaluation of Sustainability Reporting Practices: Evidence from a Cross-Country Study
Bibliographic record
Abstract
This study examines the sustainability reports (SRs)of 200 firms in both developed and emerging economies in order to identify the words most frequently used in disclosing sustainability practices within the Triple Bottom Line (TBL) approach to reporting (which emphasizes economic, environmental, and social dimensions). Its aim is to evaluate these sustainability reports under the umbrella of the GRI framework. It adopts a semi-automated Text-Mining (TM) technique to evaluate the corporate SRs of select firms from the top ten economies by GDP at current prices. Based on the GRI Standards guidelines, a total of 208 keywords were identified for analysis. The disclosures were then awarded points based on the appearance of these keywords so that the appearance of one resulted in the awarding of a score of one; if a keyword did not appear then the report was scored a zero for that word. Furthermore, a wordcloud was also generated in order to better understand the inclination of reporting language towards various TBL reporting categories. This analysis of the SRs of 200 firms from the top ten economies of the world sheds light on the differences in reporting practices and priorities as they relate to various aspects of the GRI Standards guidelines. The results indicate that SR practices have grown rapidly in the last half decade of the period selected for study (2013-2017) as compared to the first half (2008-2012). Canada ranked highest for its disclosure practices in this analysis followed by the UK, Germany, US, Japan, France, Italy, Brazil, India, and China. This study found that all included countries improved their sustainability performance over the period 2008-2017.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.029 | 0.245 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".