Corporate social responsibility, diversity, and corporate communication : natural language processing and machine learning approaches
Bibliographic record
Abstract
In the second chapter, we rely on collaborative intelligence, which combines human and artificial intelligence (i.e., supervised machine learning), to construct a textual feature that measures firmlevel gender diversity talk (GDT), as reflected in the share of gender diversity discussion in the narrative of quarterly earnings conference calls. We show that the MeToo movement, an unequivocal social movement shock, led to a significant increase in GDT. We however document positive short-term stock market reaction to GDT during the first post-MeToo quarter, indicating that GDT is, on average, perceived by investors as value-relevant. We also show that post-MeToo, high-GDT firms engage in less substantive female-friendly initiatives, indicating that firms do not walk the talk of gender diversity. In the third chapter, using industry-relevant documents and the most-cited CSR/ESG papers to develop a new CSR dictionary, we show that the COVID-19 incentivized firms to engage in overselling of their CSR. We find that more CSR talk during COVID translates into value depression, indicating that investors, on average, do not perceive CSR overselling as value-relevant. Our evidence suggests that firms do not walk their CSR talk and that CSR Talk is positively (negatively) associated with the use of positive (negative) words. Our evidence suggests that ‘cheap talk is not cheap’. \nIn the fourth chapter, we use Natural Language Processing to measure supply chain risk \n(SCR) faced by US firms, as expressed in narratives of quarterly earnings conference calls. We show that exposure to SCR reached unprecedented levels during COVID-19. The effect of COVID-19 on SCR is more pronounced in firms with a greater dispersion of analyst forecasts, increased complexity, and more financial constraints. We document a negative effect of SCR on conference call short-term returns and future profitability. High-SCR firms are also associated with longer cash conversion cycles and more ESG overselling.
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 | 0.005 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.005 |
| Science and technology studies | 0.002 | 0.006 |
| Scholarly communication | 0.008 | 0.011 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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; 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".