AI-assisted data extraction for systematic reviews in education

The application of Large Language Models (LLMs) shows significant potential to streamline and accelerate the data extraction phase of systematic reviews, particularly within the field of education. Current research indicates that LLMs can effectively extract various data types from studies, offering a path to reduce the extensive human effort traditionally required for these processes. This development is being supported by empirical studies and the iterative creation of open-source software tools.

This research addresses the inefficiency inherent in systematic review methodologies by leveraging emerging AI technologies. Accelerating the data extraction phase can significantly reduce the time and resources required to synthesize knowledge, thereby enabling faster insights and more responsive evidence-based decision-making across various domains. It also fosters the development of open-source tools, promoting wider accessibility and innovation.

Systematic reviews are labor-intensive, requiring significant human expertise for study screening and data extraction.

Forward consideration, not a verified fact.