# Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models

Source: [Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models](<https://www.sota2.com/research/paper/69d732b97d0172140ec76d0b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-10T05:00:04.898Z

Authors: Paula Dodig, Boshko Koloski, Katarina Sitar \\v{S}u\\v{s}tar, Senja Pollak, Matthew Purver

Published: 2026-04-08T08:42:02.000Z

## Abstract

Environmental, Social, and Governance (ESG) considerations are increasingly integral to assessing corporate performance, reputation, and long-term sustainability. Yet, reliable ESG ratings remain limited for smaller companies and emerging markets. We introduce the first publicly available Slovene ESG sentiment dataset and a suite of models for automatic ESG sentiment detection. The dataset, derived from the MaCoCu Slovene news collection, combines large language model (LLM)-assisted filtering with human annotation of company-related ESG content. We evaluate the performance of monolingual (SloBERTa) and multilingual (XLM-R) models, embedding-based classifiers (TabPFN), hierarchical ensemble architectures, and large language models. Results show that LLMs achieve the strongest performance on Environmental (Gemma3-27B, F1-macro: 0.61) and Social aspects (gpt-oss 20B, F1-macro: 0.45), while fine-tuned SloBERTa is the best model on Governance classification (F1-macro: 0.54). We then show in a small case study how the best-preforming classifier (gpt-oss) can be applied to investigate ESG aspects for selected companies across a long time frame.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [ESG Sentiment Analysis on SloESG-News Aspect E 1.0 (test)](<https://www.sota2.com/research/sota/esg-sentiment-analysis-on-sloesg-news-aspect-e-1-0-test.md>): ESG Sentiment Analysis; SloESG-News Aspect E 1.0 (test); Accuracy: 73.94.

- [Sentiment Analysis on SloESG-News 1.0 (test)](<https://www.sota2.com/research/sota/sentiment-analysis-on-sloesg-news-1-0-test.md>): Sentiment Analysis; SloESG-News 1.0 (test); Accuracy: 51.52.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.06826>)

[PDF](<https://arxiv.org/pdf/2604.06826.pdf>)