PRIMA-KI: Pproblem-solving learning im Mathematic teaching in primary school with AI accompany.
Didactically sound AI learning support for problem-oriented mathematics learning in primary school
A research project to develop and investigate an adaptive tutoring system for individualized learning in mathematical discovery in primary school.
About the project
As part of a project at the University of Education Weingarten (PH Weingarten), we are investigating the potentials and design possibilities of AI-powered learning companions for primary school mathematics education. Artificial intelligence offers unique opportunities for individualized, adaptive feedback in problem-based learning – provided it is designed and implemented on a sound subject-didactic foundation.
The pilot project PRIMA-AI is developing and researching prototypical AI learning companions integrated into math apps that support children in exploring and solving mathematical problems. The focus is on cognitive activation and accompanying the independent thinking process.
Project goals
- Development subject-specific didactic design principles for AI learning companions in primary school
- Development of optimally structured prompts and interaction designs for embedding in existing digital learning offerings for child-friendly, didactically meaningful adaptive support
- Identification of effective feedback strategies that reduce cognitive load and support children without replacing the learning process
- Evaluation of usage behavior and acceptance among primary school children and determination of the optimal degree of pedagogical pre-structuring of AI use for primary school children
- Creation of an evidence-based foundation for the responsible and privacy-conscious integration of AI in primary school mathematics education. Aspects of using AI with as little or anonymized data as possible are part of the research project.
Current status and planned approach
In the current pilot phase, we are focusing on the development and testing of initial prototypes in controlled settings. Through systematic variations and optimization of AI prompt designs, we are developing design guidelines and a framework for adaptive support functions based on the integration of AI learning companions into various apps by Christian Urff. Following the individual tests, more extensive field trials in school classes are planned. We welcome schools or school classes that have iPads and Wi-Fi and would like to try out the initial tests under scientific guidance. The apps will then be provided free of charge via TestFlight.
Examples and initial approaches
The Math stories uses AI to help children understand, work on, test and develop modeling tasks.
In the app number line An AI learning companion provides individualized assistance on demand or in the event of errors based on subject-didactic background knowledge. This project investigates whether and how children use this elaborated error feedback to learn from mistakes and improve number-line estimation tasks. To this end, anonymized learning data can be shared within the app for scientific evaluation.
In the app finger amounts The project investigates the support of AI in the analysis and processing of diagnostic data. AI analyzes (anonymously) strategies, flash memory times, etc., and generates short, helpful summaries for teachers to use in further support.
In the web app Calculation Field an AI-based learning companion powered by ElevenLabs accompanies the processing and is being tested there.
The conceptual framework for the question of how much guidance AI needs in learning and when it should even be used in primary school is described by the SKILL model.
Contact and collaboration
Are you interested in the project and would you like to cooperate or participate as a school or as a scientist? Then I look forward to hearing from you!
christian.urff@ph-weingarten.de