Automatic answering of scientific questions using the FACTS-V1 framework: New methods in research to increase efficiency through the use of AI

TL;DR

The paper introduces the FACTS-V1 framework, an AI-based tool for automatically extracting, analyzing, and interpreting scientific papers to enhance research efficiency and generate insights for future questions.

Contribution

It presents a novel AI-driven framework for automatic scientific paper analysis, including text extraction, filtering, interpretation, and statistical evaluation.

Findings

Successfully extracted and analyzed 82 papers on AI in education

Provided insights into how AI impacts the education sector

Demonstrated the framework's ability to support future research questions

Abstract

The use of artificial intelligence (AI) offers various possibilities to expand and support educational research. Specifically, the implementation of AI can be used to develop new frameworks to establish new research tools that accelerate and meaningfully expand the efficiency of data evaluation and interpretation (Buckingham Shum et al., 2023). This article presents the prototype of the FACTS-V1 (Filtering and Analysis of Content in Textual Sources) framework. With the help of the application, numerous scientific papers can be automatically extracted, analyzed and interpreted from open access document servers without having to rely on proprietary applications and their limitations. The FACTS-V1 prototype consists of three building blocks. The first part deals with the extraction of texts, the second with filtering and interpretation, and the last with the actual statistical evaluation (topic modeling) using an interactive overview. The aim of the framework is to provide recommendations for future scientific questions based on existing data. The functionality is illustrated by asking how the use of AI will change the education sector. The data used to answer the question comes from 82 scientific papers on the topic of AI from 2024. The papers are publicly available on the peDOCS document server of the Leibniz Institute for Educational Research and Educational Information.