首个斯洛文尼亚语ESG情感数据集及模型，助力中小企业可持续评估
Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models
- 基于大模型筛选与人工标注构建斯洛文尼亚语ESG新闻数据集
- Gemma3-27B在环境维度表现最优（F1-macro: 0.61）
- 适用于关注东欧企业可持续性的研究者与投资者
环境、社会和治理（ESG）因素日益成为评估企业绩效、声誉与长期可持续性的关键。然而，小企业和新兴市场的可靠ESG评级仍十分有限。本文首次发布公开可用的斯洛文尼亚语ESG情感数据集，并构建了一系列自动检测模型。该数据集源自MaCoCu斯洛文尼亚新闻语料库，结合大语言模型（LLM）辅助筛选与人工标注的公司相关ESG内容。我们评估了单语模型（SloBERTa）、多语模型（XLM-R）、基于嵌入的分类器（TabPFN）、分层集成架构及大型语言模型的表现。结果表明，大语言模型在环境（Gemma3-27B，F1-macro: 0.61）和社会（gpt-oss 20B，F1-macro: 0.45）方面表现最佳，而微调后的SloBERTa在治理分类中表现最优（F1-macro: 0.54）。进一步通过小规模案例研究展示最佳模型（gpt-oss）在长时段内分析特定公司ESG动态的应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。