Second Workshop on Computational Approaches to Creativity in Educational Technologies (CACE-22)

Creativity has been shown to promote students’ critical thinking, self motivation and to promote students’ mastery of skills and concepts. Despite their increasing prevalence in schools, most technological educational environments do not currently promote creativity in students’ interactions or support teachers’ ability to detect creative thinking by students. Recent work in AI and Education has began to bridge this gap from multiple perspective, such as representations (computational models for describing creativity in technology based learning environments), inference (algorithms for detecting creative outcomes from students’ interactions with these environments) and visualizations (presentations for teachers in a way that aids their understanding of students’ interactions and allow them to intervene with this process when deemed necessary). The workshop will provide a platform for researchers from different fields to share findings and discuss new research opportunities for combining AI and creativity in educational technologies. Importantly, we intend to invite a group of experts in creativity theory from the cognitive and psychological sciences to speak in the workshop. A first edition of the workshop in 2021 was very successful in attracting papers and audience.

The content and themes of the workshop, as proposed below, combine relevant research areas in the AIED and EDM communities and apply them in the new setting of promoting creativity in education. Relevant topics include, but not limited to:

• AI methods and tools for detecting and promoting creative thinking by students using technological learning environments.

• Computational models of creativity as it is reflected in students’ activities in educational software.

• Machine learning algorithms for automatically recognizing creative behaviour from students’ interactions with software.

• Planning and decision making in creativity (automatic feedback generation for student solutions).

• Transfer learning of creativity models across domains and student populations.

• Applying theoretical models of creativity to modelling students’ interactions in educational technologies.

• Visualization tools for presenting creative solutions to teachers.