Title: Approaches to integrating large data into systematic reviews and meta-analyses in education.
Abstract: As large and big sources of data and information become available, reviewers need tools and methods that allow them to retrieve, evaluate, and synthesize this information. Machine learning (ML) and individual participant data (IPD) meta-analysis can help reviewers cope with the information overflow by streamlining the identification and screening of studies, and harmonizing and standardizing the synthesis of quantitative information from large-scale studies. In this presentation, I will illustrate a methodological framework to collect, analyze, and integrate information from large-scale data sources into the systematic review and meta-analysis process. This approach aims to help reviewers cope with the information overflow in two critical stages of a research synthesis project: (a) identification and screening of studies and (b) analysis and interpretation of study results.