Application of Artificial Intelligence and Machine Learning Methods in Psychological Assessment and Analysis of Children's Drawings: Research Review
Year: 2025
Type: article
Abstract: The article is devoted to the application of artificial intelligence and machine learning methods in psychological diagnostics using drawing tests. The possibilities of modern digital technologies for automating the analysis of projective techniques, such as «Human Drawing», aimed at assessing the cognitive, emotional and social development, as well as the mental health of children and adolescents are considered. It is emphasized that the traditional interpretation of drawing tests requires high qualifications and is associated with the risk of subjectivity, while artificial intelligence and machine learning can increase the accuracy, reliability and scalability of the assessment process. The article analyzes foreign studies demonstrating the use of convolutional neural networks, large language models and multimodal approaches for processing drawings, including feature extraction, classification and forecasting of psychological states. Particular attention is paid to the validity and reliability of the tools, as well as the problem of systematic errors in machine learning models. A general description of artificial intelligence and machine learning methods as applied to image analysis and, in particular, children's drawings is provided. Examples of successful application of artificial intelligence for analysis of children's drawings in the context of assessment of post-traumatic stress, cognitive and motor skills are given. The study highlights the interdisciplinary nature of the approach, combining psychology and engineering sciences, and the prospects for further development of automated tools for psychological diagnostics.
Authors: M.G. Sorokova, E.V. Filippova, M.V. Bulygina, A.S. Alekseychuk
Language: English
Subfield: Applied Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4414859022