The Frontiers of Society, Science and Technology, 2026, 8(4); doi: 10.25236/FSST.2026.080405.
Bin Wang
Department of Computer Science, School of Intelligent Science and Engineering, Xi'an Peihua University, Xi'an, Shaanxi, China
Automated creativity scoring is spreading through schools as advice about choosing a tool, yet any tool, however well validated, can only score fairly what a task elicits. This article addresses the other half of the practice: the design of divergent-thinking tasks for AI-based scoring algorithms. Six task-design recommendations are proposed and developed: anchoring the task in an established divergent-thinking family, matching the response format to the declared capability of the scoring tool, fixing a level-anchored rubric before responses are collected, stating the unit of scoring and bounding response length, piloting the task against a small human-scored sample, and using fresh, curriculum-local item content. Each recommendation names the action, the rationale, and the consequence for score interpretation. A worked example carries one task from design brief to classroom deployment, and a closing section marks the limits of task-side effort. A task built this way gives a validated tool something meaningful to score and gives teachers a stable basis for reading the numbers.
divergent thinking; creativity assessment; task design; automated scoring; artificial intelligence in education
Bin Wang. Designing Divergent-Thinking Tasks for AI-Based Scoring Algorithms. The Frontiers of Society, Science and Technology (2026), Vol. 8, Issue 4: 28-32. https://doi.org/10.25236/FSST.2026.080405.
[1] Guilford, J. P. (1967). The Nature of Human Intelligence. McGraw-Hill.
[2] Torrance, E. P. (1974). Torrance Tests of Creative Thinking: Norms-Technical Manual. Scholastic Testing Service.
[3] Runco, M. A., & Acar, S. (2012). Divergent Thinking as an Indicator of Creative Potential. Creativity Research Journal, 24(1), 66-75.
[4] Runco, M. A., Millar, G., Acar, S., & Cramond, B. (2010). Torrance Tests of Creative Thinking as Predictors of Personal and Public Achievement: A Fifty-Year Follow-Up. Creativity Research Journal, 22(4), 361-368.
[5] Kim, K. H. (2011). The Creativity Crisis: The Decrease in Creative Thinking Scores on the Torrance Tests of Creative Thinking. Creativity Research Journal, 23(4), 285-295.
[6] Amabile, T. M. (1982). Social Psychology of Creativity: A Consensual Assessment Technique. Journal of Personality and Social Psychology, 43(5), 997-1013.
[7] Silvia, P. J., Winterstein, B. P., Willse, J. T., Barona, C. M., Cram, J. T., Hess, K. I., Martinez, J. L., & Richard, C. A. (2008). Assessing Creativity with Divergent Thinking Tasks: Exploring the Reliability and Validity of New Subjective Scoring Methods. Psychology of Aesthetics, Creativity, and the Arts, 2(2), 68-85.
[8] Plucker, J. A., Qian, M., & Wang, W. (2011). Is Originality in the Eye of the Beholder? Comparison of Scoring Techniques in the Assessment of Divergent Thinking. The Journal of Creative Behavior, 45(1), 1-22.
[9] Landauer, T. K., Foltz, P. W., & Laham, D. (1998). An Introduction to Latent Semantic Analysis. Discourse Processes, 25(2-3), 259-284.
[10] Beaty, R. E., & Johnson, D. R. (2021). Automating Creativity Assessment with SemDis: An Open Platform for Computing Semantic Distance. Behavior Research Methods, 53(2), 757-780.
[11] OECD. (2023). PISA 2022 Assessment and Analytical Framework. OECD Publishing.