josephagossa/KenyaESG-RoBERTa-gov

KenyaESG-RoBERTa-gov

Binary sentence classifier for Governance (=gov) ESG communication in corporate reports of firms listed on the Nairobi Securities Exchange (NSE). One of three independent pillar models (env, soc, gov), following the sentence-level design of Schimanski et al. (2024).

Intended use

Classify a report sentence as gov=1 (governance content present) or 0. Aggregating the predictions over all sentences in a report yields a firm-year governance disclosure score (the proportion of governance sentences). The three pillar classifiers are applied independently, so a sentence may be positive on more than one pillar.

Training data

3,900 unique sentences (the 100-sentence human evaluation set is held out): reviewed NSE/Kenyan sentences plus reference sentences from Schimanski et al. (2024). Kenyan labels were assigned by keyword filtering refined by a single-reviewer pass — not full manual annotation. Decision threshold 0.5; base model roberta-base; maximum sequence length 256.

How to use

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

repo = "josephagossa/KenyaESG-RoBERTa-gov"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForSequenceClassification.from_pretrained(repo)

text = "The board audit committee strengthened internal controls and the anti-corruption compliance framework."
inputs = tok(text, return_tensors="pt", truncation=True, max_length=256)
with torch.no_grad():
    prob = torch.softmax(model(**inputs).logits, dim=-1)[0, 1].item()
label = int(prob >= 0.5)   # 1 = governance content present
print(label, round(prob, 3))

Evaluation

Held-out human benchmark, n = 100 sentences, scored against a two-annotator adjudicated ground truth that is independent of the keyword training labels.

Limitations

Captures disclosure intensity, not substantive quality. Conservative and precise: a high governance score is highly credible; a low one may under-count borderline disclosures. Trained on English-language NSE reports; cross-market and cross-language generalisation is untested. Labels derive from a keyword filter plus a single-reviewer pass rather than full manual annotation.

Citation

If you use this model, please cite the accompanying paper and the reference dataset.

This model

@misc{agossa2026kenyaesg_gov,
  author       = {Agossa, Joseph},
  title        = {KenyaESG-RoBERTa-gov},
  year         = {2026},
  publisher    = {Hugging Face},
  doi          = {10.57967/hf/9128},
  url          = {https://doi.org/10.57967/hf/9128}
}

Paper

Agossa, J. (2026). Pricing the Cost of Compliance: Equity Reactions to Mandatory ESG Disclosure in a Frontier Market. Working paper. SSRN: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6966682

@unpublished{agossa2026compliance,
  author = {Agossa, Joseph},
  title  = {Pricing the Cost of Compliance: Equity Reactions to
            Mandatory ESG Disclosure in a Frontier Market},
  year   = {2026},
  note   = {Working paper, SSRN 6966682},
  url    = {https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6966682}
}

Reference sentences

Schimanski, T., Reding, A., Reding, N., Bingler, J., Kraus, M., & Leippold, M. (2024). Bridging the gap in ESG measurement: Using NLP to quantify environmental, social, and governance communication. Finance Research Letters, 61, 104979.

@article{schimanski2024bridging,
  author  = {Schimanski, Tobias and Reding, Andrin and Reding, Nico and
             Bingler, Julia and Kraus, Mathias and Leippold, Markus},
  title   = {Bridging the gap in {ESG} measurement: Using {NLP} to quantify
             environmental, social, and governance communication},
  journal = {Finance Research Letters},
  volume  = {61},
  pages   = {104979},
  year    = {2024}
}