Semantic measures in design conversations as predictors of creative outcomes in design education

The analysis of conversations maintained during the design activity can help to gain a better insight into design thinking and its relation to creativity. A semantic analysis approach was employed to inspect the content of communications and information exchange between students and instructors. The goal was to explore design conversations in terms of Abstraction, Polysemy, Information Content and Semantic Similarity measures, and analyse their relation to the creativity of final design outcomes. These were assessed according to their Originality, Usability, Feasibility, Overall Value and Overall Creativity. To this end, design conversations from the 10th Design Thinking Research Symposium (DTRS10) dataset were used. Main results show a significant relationship between Information Content and Originality and Overall Creativity. For instructors, Semantic measures were mainly related to Feasibility, whereas for students the focus was set on the Overall Value of the final solutions.