First impressions on sustainable innovation matter: Using NLP to replicate B-lab environmental index by analyzing companies' homepages
Bibliographic record
Abstract
This study explores the potential for developing web-based environmental culture indicators by analyzing signals extracted from the homepages of company websites. The primary aim is to assess the proposed method's ability to generate indicators that can serve as proxies for real environmental measures by leveraging the homepage content. We performed a Zero-Shot Text Classification (ZSTC) using a BERT-type Natural Language Processing (NLP) model, followed by a regression analysis to test the ability of these web-based indicators to replicate the B-Lab environmental index and comprehend the dynamics behind the results. This pilot study explains 57 % of the variance of the B-Lab environmental index using the results of the ZSTC score and companies' characteristics. This research makes two significant contributions. First, the text content of a company's homepage seems to provide insights into its environmental performance. Second, it introduces a generalizable methodology for studying the performance of companies through their websites without the need for heavy pre-processing, significantly reducing the time and cost of research. Furthermore, the method could provide policymakers with a real-time landscape to create and finetune policies about specific topics, partially addressing the problems associated with questionnaire-based surveys.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.030 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".