Deep Multi-label Classification of Personality with Handwriting Analysis

Handwriting analysis has traditionally been used to infer personality traits from the stylistic features of writing. With advances in machine learning, the accuracy and applicability of these analyses have significantly improved. This paper presents a new multi-label classification approach to classify personality traits, such as Extraversion and Conscientiousness, into Low, Average, and High categories. This approach uses Binary Cross-Entropy with Logits Loss and Focal Loss to handle multi-label classification and class imbalance. Image segmentation techniques are also employed to enhance the handling of limited handwriting samples. The paper evaluates the complexity and performance of ResNet-50 and ResNet-101 architectures in recognizing complex handwriting patterns using three optimizers: SGD with momentum, Adam, and AdaBelief. The results demonstrate the efficacy of our proposed method, improving overall accuracy from 67.09% to 90.16% for ResNet-50 and from 69.43% to 90.07% for ResNet-101, with an overall AUC of 0.96. These improvements emphasize the model's capability for practical automated handwriting analysis.