Automated Personality Prediction through Hindi Handwriting Analysis: A Machine Learning Approach to Graphology
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, the study of handwriting, offers a window into understanding human personality by analysing writing patterns and strokes. For Hindi characters, this analysis takes on a unique dimension due to the distinct structure and aesthetics of the Devanagari script. Each character's intricate curves, alignment, and spacing can reveal valuable insights into a person's emotional state, thought patterns, and personality traits. This study proposes an automated system tailored to Hindi handwriting graphology, aiming to predict key personality traits by extracting handwriting features specific to the script.
The system evaluates aspects such as character size, slant angle, baseline consistency, pen pressure variations, spacing between characters and words, and margin alignment. These features are processed using advanced machine learning techniques, with a LGBM Classifier model employed to classify five core personality traits. The model leverages the unique characteristics of Hindi script to improve the accuracy of predictions, providing an efficient and scalable alternative to traditional graphological analysis.
This approach not only broadens the scope of handwriting analysis to regional languages but also sets a foundation for further advancements in personality prediction through linguistic diversity.
Open the resolved locator · 10.1145/3772673.3772676
Metadata licence: OpenAlex metadata (CC0)