Construction and Validation of a Computerized Creativity Assessment Tool With Automated Scoring Based on Deep-Learning Techniques

Based on the divergent thinking (DT) framework of creativity assessment, this study constructed the Computerized Creativity Assessment with Figure Test (C-CRAFT) that is equipped with an automated scoring system and built around a deep-learning-based semantic space model called Word2Vec. A subject pool of 493 undergraduates completed the C-CRAFT as well as a conventional paper-and-pencil DT test that required manual scoring. We found moderately high to high coefficients for the correlations between the two tests, which suggested that the C-CRAFT has strong criterion-related validity. The results of the pre and posttests also demonstrated the high test–retest reliability of the C-CRAFT. Good discriminant validity was evidenced by highly significant differences in the C-CRAFT scores between college students from art and design-related fields and students from other majors. These research findings indicate that the C-CRAFT is a valid and reliable assessment tool for DT, while the automated nature of the C-CRAFT makes it easier to implement the DT test compared with traditional approaches. Moreover, by applying the C-CRAFT to the Chinese language, this study contributes to the cross-linguistic research of semantic models in creativity assessment.