Leveraging neural networks for creativity measurement and enhancement in educational settings

In the realm of 21 st century education, creativity is widely regarded as one of the essential qualities that students must possess. With the increasing demand for personalized teaching, accurately measuring students’ creativity and effectively enhancing it has become a focal point of current educational research. Traditional methods of educational assessment fall short in terms of personalized recommendations and long-term effect evaluation, failing to meet the needs of modern education. In contrast, the potential exhibited by artificial intelligence technologies, especially neural networks in data processing and behavioral analysis, offers new possibilities for addressing these issues. The efficiency and flexibility of Graph Attention Networks (GANs) in handling complex relational data, in particular, provide novel tools for the scientific measurement and enhancement of creativity. However, existing research is insufficient in exploring the impact of group interactions on creativity and assessing the long-term effects of personalized educational interventions. This study initially utilizes GANs to establish an innovative model for group activity recommendation, aimed at analyzing students’ personality traits and levels of creativity to recommend activities best suited for unleashing their creative potential. Subsequently, a weighted network approach is employed to quantitatively analyze the effectiveness of creative enhancement following participation in recommended activities, examining the impact of various educational intervention strategies. This research not only extends the application of neural networks in the field of education but also offers new methodological support for personalized teaching, holding significant theoretical and practical implications for optimizing educational resource allocation and enhancing educational quality.