A Comparative Study of Machine Learning Algorithms for Handwriting-Based Personality Trait Prediction
Parth Bhatnagar, Manjit Singh Sodhi, Sailendra Panigrahi · Asia Conference on Machine Learning and Computing (ACMLC) · 2025
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Asia Conference on Machine Learning and Computing (ACMLC) · OpenAlex · conference-paper · 2025
Abstract
Graphology, a scientific discipline, seeks to identify, evaluate, and understand human personality traits by analyzing handwriting strokes and patterns. Handwriting can reveal insights into an individual's true character, such as emotional tendencies, fears, honesty, defenses, and other attributes. Professional handwriting analysts, known as graphologists, often possess the skill to discern the identity of the writer through handwriting samples. However, the accuracy of such analysis largely depends on the analyst's expertise. The proposed system employs four algorithms to analyses handwriting for predicting eight distinct personality traits of a writer.
These algorithms include: (i) Snap Boosting Machine Classifier, (ii) Snap Random Forest Classifier, (iii) Decision tree classifier, and (iv) Snap Logistic Regression. Additionally, these methods are evaluated based on various performance metrics, including the ROC curve, confusion matrix, and others. Key observations and respective conclusions have been derived from the analysis.
Open the resolved locator · 10.1145/3772673.3772675
Metadata licence: OpenAlex metadata (CC0)