Neutrosophic Stance Detection and fsQCA-Based Necessary Condition Analysis for Causal Hypothesis Assessment in AI-Enhanced Learning

Abstract

The use of artificial intelligence (AI) in educational settings has attracted increasing scholarly attention, although applicable empirical findings are scarce and contradictory. This study seeks to resolve the ambiguities surrounding AI in education through a methodological contribution, merging neutrosophic stance detection and Fuzzy Set Qualitative Comparative Analysis (fsQCA). Neutrosophic analysis enables explicit modeling of truth, uncertainty/indeterminacy, and falsity, while merging these findings through fsQCA creates a relative explanation of existing research findings. After evaluating four causal hypotheses related to AI-based learning opportunities through a Consensus Meter, a research survey with 24 university participants explored the necessary conditions regarding the experience of improvements in learning outcomes. The findings indicate that the digital divide is a necessary and sufficient condition for an effective educational experience with AI. Furthermore, necessary conditions for AI feedback and the use of AI-based platforms emerge; however, the effectiveness of these platforms generates significant uncertainty. Ultimately, the neutrosophic-fsQCA framework provides a viable technique for synthesizing ambiguous findings through a systematic approach. Empirically, the results reveal that all actors involved in potential AI-based learning must ensure digital equity and high-quality design for interactive experiences to benefit from the successful integration of AI in education.