← 論文一覧に戻る

欧州上場銀行のESG分析のための年次報告書テキストコーパスと再現資料、2013-2023年

Annual Report Text Corpus and Replication Materials for ESG Analysis of European Listed Banks, 2013–2023 (原題)

Dara Ghahremani

Zenodo (CERN European Organization for Nuclear Research)データセット2026-08-18#AI×ESGOrigin: EU対象セクター: finance
DOI: 10.5281/zenodo.21993748
原典: https://doi.org/10.5281/zenodo.21993748

🤖 gxceed AI 要約

日本語

欧州上場銀行の年次報告書テキストコーパスとESG分析の再現資料を提供する。PDFからテキスト変換、ESG辞書による分類、用語密度測定などの手法を公開し、ESG開示研究の透明性と再現性を高める。

English

This repository provides a machine-readable corpus of annual reports from European listed banks (2013-2023), along with scripts and an ESG dictionary for text analysis. It supports reproducible ESG disclosure research, including term-density measures and thematic identification.

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開示が始まり、ESG情報のテキスト分析の重要性が増す。本コーパスは手法の参考となり、日本語コーパス構築のひな型となる。

In the global GX context

Globally, this supports the growing need for standardized ESG text analysis, aligning with ISSB and CSRD disclosure requirements. It provides a replicable methodology for analyzing corporate reports.

👥 読者別の含意

🔬研究者:ESG開示のテキスト分析手法と再現可能なデータセットを活用できる。

🏢実務担当者:自社の開示テキストを分析する際の辞書や手法の参考になる。

📄 Abstract(原文)

This repository contains the annual-report text corpus, data-processing scripts, ESG classification materials, and derived outputs used in the empirical analysis of ESG disclosure and performance among European listed banks over the period 2013–2023. The annual-report corpus was compiled from publicly available annual reports issued by the sampled European banks. The original PDF reports were converted into machine-readable plain text using pdf2txt to facilitate automated textual analysis. The resulting text files were organised by bank and year. The repository includes the machine-readable annual-report text corpus, scripts used for PDF-to-text conversion and textual processing, ESG-related output files, and the ESG master dictionary used to classify and analyse relevant terminology. The materials support the transparency and reproducibility of the research methodology described in the associated PhD thesis. The textual analysis includes ESG term-density measures and supports the identification and interpretation of sustainability, governance, risk, materiality and related disclosure themes. The original annual reports are third-party publications and may be subject to their respective copyright and usage conditions. Where applicable, the repository provides processed research materials rather than redistributing the original reports. Data and materials are provided for academic research and reproducibility purposes.

🔗 Provenance — このレコードを発見したソース

🔔 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。