dataBERT: AI-Assisted Framework for Sustainable Investment Concept Discovery

59.6 KB of data supporting an AI-assisted framework for inductive theory building in sustainable investment research. The dataset, created by Gunawan Wibisono and last updated in April 2026, was derived from a Scopus-screened corpus of academic literature. It models an integrative conceptual architecture organized around cognitive, structural, and bridge mechanisms.

Use Cases

• Semantic topic discovery in sustainable investment literature based on the described BERTopic methodology.
• Construct surfacing and relationship mapping based on the described use of spaCy for named entity recognition.
• Abductive synthesis for theory building based on the described researcher-led interpretive workflow.
• Analyzing conceptual fragmentation across ESG, SRI, and green finance domains as mentioned in the description.

Strengths

• Dataset is 59.6 KB, indicating a focused and manageable size for initial exploration.
• The methodological workflow is transparently described, involving structured corpus construction and robustness assessment.
• Released under a permissive CC-BY-4.0 license, allowing for broad reuse and modification.

Limitations

• Row count and column-level documentation are unknown, which may limit suitability assessment.
• The dataset's 59.6 KB size suggests a limited scope, potentially containing only model outputs or summary statistics rather than a full corpus.
• Description metadata is limited; actual data quality and structure require manual inspection after download.

Provenance

Source

Gunawan Wibisono via figshare

Collection Method

Corpus identified through a Scopus search, screened for conceptual relevance, with paragraph-level modeling using BERTopic and spaCy.

Freshness

Last updated 2026-04-15 18:03:50