Skip to content„Lass dich nicht unterkriegen; sei frech und wild und wunderbar!“— Pippi LangstrumpfMartin SchäpeLearning support & teaching materials

← Forschung/Project Status

Master's Thesis: AI in General Studies

Titelgrafik der Masterarbeit

Publication

Open access

KI-gestützte Informationsrecherche und Selbstwirksamkeit im inklusiven Sachunterricht: Eine qualitative Studie zum scaffolding-basierten Einsatz multimodaler KI-Tools in heterogenen Lerngruppen der Klasse 3/4

Master's thesis (M.Ed.) · Bielefeld University · Publication version 1.0 · published on Zenodo on 4 November 2026 · written in German

Read & download on ZenodoDOI 10.5281/zenodo.23940355

Suggested citation (APA 7)

Schäpe, M. (2026). KI-gestützte Informationsrecherche und Selbstwirksamkeit im inklusiven Sachunterricht: Eine qualitative Studie zum scaffolding-basierten Einsatz multimodaler KI-Tools in heterogenen Lerngruppen der Klasse 3/4 [Master's thesis, Bielefeld University]. Zenodo. https://doi.org/10.5281/zenodo.23940355

License

CC BY 4.0 – share and adapt with attribution.

Excluded are the teaching materials in Appendices B and D, which are available separately on eduki.

What happens to the experience of self-efficacy and the handling of mistakes when primary school children use an AI voice assistant as a research tool? The central idea: AI does not judge. Children can ask, try out, and correct — at their own pace.

Methodological Approach

Empirical Data Collection

Data were collected at two schools during regular primary science lessons (48 children, years 3 to 5). The children used school-provided AI assistants for research. Only children whose parents gave written consent were recorded; the data are pseudonymised.

Qualitative Analysis & Progression Types

The data is analyzed qualitatively using MAXQDA. Through coding the interactions, specific progression types (Verlaufstypen) were identified, showing how children adapt search strategies and deal with errors. These cognitive processes can be modeled through the iterative and the double EVA cycle (Input – Processing – Output).

Project timeline

Exposé & Concept Development

Completed

Approval & School Planning

Completed

Data Collection in Schools

Completed

Qualitative Analysis (MAXQDA)

Completed

Writing & Polishing

Completed

Submission (Sep 18, 2026)

Completed

Publication (open access, Nov 4, 2026)

Completed

Visualization of Cognitive Models

Analyse-Raster EVA-KI (Verlaufstypen)

Analyse-Raster EVA-KI für Verlaufstypen

Scaffolding-Heuristik

Scaffolding Heuristik

Code-Schema SE-KI (Methodik)

Code-Schema SE-KI: Methodik und Codierregeln

Code-Schema SE-KI (Kategorien)

Code-Schema SE-KI: Auswertungslogik und Cluster