Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914457583616000 |
|---|---|
| author | Dodig, Paula Koloski, Boshko Šuštar, Katarina Sitar Pollak, Senja Purver, Matthew |
| author_facet | Dodig, Paula Koloski, Boshko Šuštar, Katarina Sitar Pollak, Senja Purver, Matthew |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06826 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models Dodig, Paula Koloski, Boshko Šuštar, Katarina Sitar Pollak, Senja Purver, Matthew Computation and Language Artificial Intelligence 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. |
| title | Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06826 |