From Text Analysis to Metrics: AI Approaches to ESG Assessment
テキスト分析から指標へ：ESG評価へのAIアプローチ (AI 翻訳)
Qianxing Chen
🤖 gxceed AI 要約
日本語
本論文は、ESG評価におけるAIモデルの進化を概説し、トピックモデルからドメイン適応型Transformer、検索拡張言語モデルへの移行を追跡する。ニュース、決算説明会、レポートからのマルチラベルフレーズアノテーションに焦点を当て、非ESGコントロール、業界マテリアリティ、財務センチメントを統合する。精度・再現率、外部妥当性、格付機関間の構造的差異を考慮した評価を行う。最終的に、テキスト→メトリクス→計量経済学のアプローチを提案し、ESG測定のスケーラビリティ、適時性、比較可能性、監査可能性を向上させる。
English
This paper traces the evolution of AI models for ESG assessment, from topic models to domain-adaptive Transformers and retrieval-augmented language models. It focuses on multi-label phrase annotation from news, earnings calls, and reports, integrating non-ESG controls, industry materiality, and financial sentiment. Evaluation considers precision/recall, external validity, and structural differences among rating agencies. The proposed 'text → metrics → econometrics' approach improves scalability, timeliness, comparability, and auditability of ESG measurement.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではSSBJや有報でのESG情報開示が進む中、AIによるテキスト分析でスケーラブルな指標生成が可能になれば、開示の実効性向上に貢献する。特に業界マテリアリティの組み込みは日本企業の統合報告書にも応用可能。
In the global GX context
This survey directly addresses global disclosure needs under TCFD, ISSB, and CSRD, where timely and auditable ESG metrics are critical. Its focus on retrieval stability and cross-lingual robustness is relevant for multinational reporting and consistency across jurisdictions.
👥 読者別の含意
🔬研究者:Provides a comprehensive taxonomy of AI methods for ESG text analysis, useful for designing novel approaches or benchmarking existing systems.
🏢実務担当者:Offers insights for automating ESG data extraction from corporate reports and news, improving supply chain screening and investor analysis.
🏛政策担当者:Highlights the need for benchmark design and validation standards for AI-based ESG metrics, relevant for regulators considering disclosure technology.
📄 Abstract（原文）
In ESG assessments, disclosure-centric scorecards are being replaced by AI-based sentence-level systems, which offer organized aggregate based on precise criteria. The shift from topic models and human supervision to domain-adaptive Transformer classifiers and evidence-based language models with retrieval capabilities is traced in this work. In order to create trustworthy textual metrics from news, earnings calls, and reports, we concentrate on multi-label phrase annotation by combining non-ESG controls, industry materiality, and financial sentiment. The evaluation takes precision/recall, external validity, and structural variations among rating agencies into account. Decision-making applications in supply chain visibility, investment research, and disclosure assurance are covered, as well as governance elements like documentation, energy use, and human-computer interaction. We conclude by outlining potential avenues for future research and development, such as cross-lingual robustness, retrieval stability, benchmark design, and low-carbon AI. Our suggested "text → metrics → econometrics" approach complements current ratings while improving the scalability, timeliness, comparability, and auditability of ESG measurement.
🔗 Provenance — このレコードを発見したソース
- openaire https://doi.org/10.54097/wr1teh04first seen 2026-07-18 05:10:28
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。