A Pathway for Assessing Grey Literature: Leveraging AI to Extract Conference Metadata and Organiser Information from Calls for Papers

A new AI-based framework, COCI, has been developed to automate the extraction of structured metadata from unstructured Calls for Papers (CfPs), a form of grey literature. This framework utilizes Large Language Models (LLMs) to process highly heterogeneous text, overcoming limitations of traditional tools and enabling systematic analysis of previously overlooked data sources for Metascience and Scientometric studies.

Why it matters

The development of AI-based tools like COCI offers a pathway to systematically analyze vast amounts of previously inaccessible grey literature. This capability can enhance strategic decision-making by providing deeper insights into emerging research trends, critical stakeholders, and the evolving landscape of academic and professional discourse across various domains. Such insights are crucial for understanding innovation pathways and identifying nascent areas of development.

Key insights

• Grey literature, such as Calls for Papers (CfPs), is largely overlooked in Metascience and Scientometric analysis due to its unstructured and heterogeneous format.
• Traditional tools are ineffective at processing unstructured grey literature at scale.
• Large Language Models (LLMs) provide a new opportunity to systematically harvest and process this type of data.
• COCI is an AI-based framework designed to automate the extraction of granular, structured metadata from raw CfP text.
• The COCI framework employs a multi-stage pipeline for entity extraction, author disambiguation (using OpenAlex), and semantic mapping of topics and conference series.

Source

arXiv — Computers and Society — https://arxiv.org/abs/2608.24926