Artificial intelligence for personality prediction based on handwriting and signature: a systematic review

Ibañez-Chanamé R.J.; Aquino-Trujillo J.Y. · Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology (2024) · DOI: 10.18687/leird2024.1.1.355

Resumen

Artificial intelligence (AI) is increasingly being used to assess personality in various contexts. Therefore, this study focuses on identifying and evaluating the most effective techniques in computational graphology. An exhaustive search was carried out in scopus, reviewing articles published between 2014 and 2024 using the PRISMA methodology, selecting 29 articles and 6 additional ones through citation extraction, from a total of 1262 records. The results highlighted the difficulty of manual feature extraction, which is prone to errors. However, advanced AI techniques such as machine learning and deep learning are significantly improving the accuracy of interpreting graphological features. Therefore, a wide variability in the accuracy of the techniques was observed, with some showing high levels of accuracy, while others had difficulties in generalizing results across different datasets. This review provides a solid foundation for future research and practical applications in computational graphology.

Instituciones: Universidad Tecnológica del Perú