PREDICTIVE MODELS FOR CREATIVE TALENT IDENTIFICATION
DOI:
https://doi.org/10.29121/shodhkosh.v6.i1s.2025.6666Keywords:
Creativity Assessment, Multimodal Learning, Predictive Modeling, Deep Learning, Feature Fusion, Creative Talent Identification, Explainable AI, Behavioural AnalyticsAbstract [English]
Creative talent is a multidimensional human ability that cannot be evaluated fully by traditional assessments based solely on portfolios, standardised tasks or subjective evaluation. In this paper, a multimodal predictive architecture is proposed that fuses textual, visual and behavioural data to predict creative potential more accurately, at a scale and with fairness that is achievable to human standards. In particular, it uses language models based on transformers, vision transformers, and behavioral encoders at the sequence level to learn latent representations of creativity (e.g., in the form of story divergence, in visual novelty, and in terms of exploratory interaction patterns). An attention-based feature integration factorizes modality-specific representations into a single representation, but the attention structure makes it possible to adaptively weight modalities to individual creative styles, instead of forcing creators to express themselves through a single process. Experimental results show that the multimodal model is able to perform much better than unimodal baselines, with both high accuracy, high correlation with expert scores, and robust cross-trials. Furthermore, the analysis of its interpretability suggests that the decisions made by the model align well with the human-recognized creative features, verifying its interpretability and its ethical suitability. This research draws attention to the possibility of AI-driven multimodal systems to improve talent identification of creative people, to provide a more inclusive and data-informed approach for applications in education, recruitment, and the creative industries.
References
Ali, S. R., and Sahar, A. (2025). Respiratory Rate Estimation and ECG-Derived Respiration Techniques—A Review. IJEECS, 14(1), 137–139.
Brandes, N., Ofer, D., Peleg, Y., Rappoport, N., and Linial, M. (2022). ProteinBERT: A Universal Deep-Learning Model of Protein Sequence and Function. Bioinformatics, 38(8), 2102–2110. https://doi.org/10.1093/bioinformatics/btac020 DOI: https://doi.org/10.1093/bioinformatics/btac020
El Janati, S., Maach, A., and El Ghanami, D. (2019). Context Aware in Adaptive Ubiquitous E-Learning System for Adaptation Presentation Content. Journal of Theoretical and Applied Information Technology, 97, 4424–4438.
Greene, R. T. (2023). The Future of Instructional Design: Engaging Students Through Gamified, Personalized, and Flexible Learning with AI and Partnerships. e-Learning Industry.
Huang, G., An, J., Yang, Z., Gan, L., Bennis, M., and Debbah, M. (2024). Stacked Intelligent Metasurfaces for Task-Oriented Semantic Communications. IEEE Wireless Communications Letters. Advance online publication. https://doi.org/10.1109/LWC.2024.3499970 DOI: https://doi.org/10.1109/LWC.2024.3499970
Lhafra, F. Z., and Otman, A. (2023). Integration of Evolutionary Algorithm in an Agent-Oriented Approach for an Adaptive E-Learning. International Journal of Electrical and Computer Engineering, 13(2), 1964–1978. https://doi.org/10.11591/ijece.v13i2.pp1964-1978 DOI: https://doi.org/10.11591/ijece.v13i2.pp1964-1978
Lincke, A., Jansen, M., Milrad, M., and Berge, E. (2019). Using Data Mining Techniques to Assess Students’ Answer Predictions. In Proceedings of the 27th International Conference on Computers in Education (ICCE 2019) (pp. 42–50). https://doi.org/10.58459/icce.2019.285 DOI: https://doi.org/10.58459/icce.2019.285
Miller, T. (2023). Explainable AI is Dead, Long Live Explainable AI! Hypothesis-Driven Decision Support Using Evaluative AI. In Proceedings of the ACM Conference on Fairness, Accountability, and Transparency (FAccT ’23) (pp. 333–342). https://doi.org/10.1145/3593013.3594001 DOI: https://doi.org/10.1145/3593013.3594001
Rao, R., Bhattacharya, N., Thomas, N., Duan, Y., Chen, P., Canny, J., Abbeel, P., and Song, Y. (2019). Evaluating Protein Transfer Learning with TAPE. In Advances in Neural Information Processing Systems (Vol. 32). https://doi.org/10.1101/676825 DOI: https://doi.org/10.1101/676825
Riad, M., Gouraguine, S., Qbadou, M., and Aoula, E.-S. (2023). Towards a New Adaptive E-Learning System Based on Learner’s Motivation and Machine Learning. In Proceedings of the 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET 2023) (pp. 1–6). https://doi.org/10.1109/IRASET57153.2023.10152884 DOI: https://doi.org/10.1109/IRASET57153.2023.10152884
Seo, K., Tang, J., Roll, I., Fels, S., and Yoon, D. (2021). The Impact of Artificial Intelligence on Learner–Instructor Interaction in Online Learning. International Journal of Educational Technology in Higher Education, 18, Article 54. https://doi.org/10.1186/s41239-021-00292-9 DOI: https://doi.org/10.1186/s41239-021-00292-9
Wang, S., Wu, H., Kim, J. H., and Andersen, E. (2019). Adaptive Learning Material Recommendation in Online Language Education. In S. Isotani et al. (Eds.), Artificial Intelligence in Education (AIED 2019) (Lecture Notes in Computer Science, Vol. 11626). Springer. https://doi.org/10.1007/978-3-030-23207-8_55 DOI: https://doi.org/10.1007/978-3-030-23207-8_55
Wang, Z., Wang, Z., Xu, Y., Wang, X., and Tian, H. (2023). Online Course Recommendation Algorithm Based on Multilevel Fusion of User Features and Item Features. Computer Applications in Engineering Education, 31, 469–479. https://doi.org/10.1002/cae.22592
Wang, Z., Wang, Z., Xu, Y., Wang, X., and Tian, H. (2023). Online Course Recommendation Algorithm Based on Multilevel Fusion of User Features and Item Features. Computer Applications in Engineering Education, 31, 469–479. https://doi.org/10.1002/cae.22592 DOI: https://doi.org/10.1002/cae.22592
Yao, C., and Wu, Y. (2022). Intelligent and Interactive Chatbot Based on the Recommendation Mechanism for Personalized Learning. International Journal of Information and Communication Technology Education, 18, 1–23. https://doi.org/10.4018/IJICTE.315596 DOI: https://doi.org/10.4018/IJICTE.315596
Zilinskiene, I., Dagiene, V., and Kurilovas, E. (2012). A Swarm-Based Approach to Adaptive Learning: Selection of a Dynamic Learning Scenario. Academic Conferences International Limited.
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Bhagyalaxmi Behera, Priyadarshani Singh, Dr. Shashikant Patil, Sulabh Mahajan, Romil Jain, Divya S Khurana
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
