Mobile-Based Big Five Personality Score Prediction from Handwriting Using VGG19

Maharani Sekar Hapsari, Salamun Rohman Nudin

Abstract


Handwriting is a non-verbal approach that can be used to identify an individual’s personality traits. However, manual scoring methods still involve subjectivity and require specialized skills; therefore, a more objective, efficient, and consistent automated approach is needed. This study aims to develop a system for predicting personality scores based on handwriting images. The personality dimensions used refer to the Big Five Personality traits, namely Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. The research methodology applies an adaptation of the CRISP-DM framework, which includes the stages of business understanding, data analysis, data preparation, model development, evaluation, and system implementation. This study employs the VGG19 architecture by comparing three optimizers: Adam, SGD, and RMSProp. Evaluation results indicate that the RMSProp optimizer achieved the best performance on the validation data, with an MSE of 0.0128, MAE of 0.0930, RMSE of 0.1133, PCC of 0.4648, and accuracy of 90.70%. The VGG19 model with RMSProp as the best optimizer was subsequently implemented into a mobile application capable of receiving handwriting image inputs and generating personality score predictions. This study demonstrates that the integration of Deep Learning and mobile applications has the potential to serve as a practical solution for predicting Big Five Personality scores based on handwriting.

Keywords


Big Five Personality, VGG19; Deep Learning; Handwriting; Mobile Application

Full Text:

PDF

References


C. Suman, S. Saha, A. Gupta, S. K. Pandey, dan P. Bhattacharyya, “A Multi-Modal Personality Prediction System,” Knowledge-Based Syst., Vol. 236, 2022, DOI: 10.1016/j.knosys.2021.107715.

K. Brauer dan R. Sendatzki, “The Interview as an Assessment Method in Psychology,” Insp. Interview, hal. 137–160, 2024, DOI: 10.1515/9783111086484-009.

S. Nazari, W. L. Leite, dan A. C. Huggins-Manley, “A Comparison of Person-Fit Indices to Detect Social Desirability Bias,” Educ. Psychol. Meas., Vol. 83, No. 5, hal. 907–928, 2023, DOI: 10.1177/00131644221129577.

V. Ghods, “Personality Recognition based on Handwriting Types using Fuzzy Inference,” IEEE Access, vol. 11, no. July, hal. 86456–86469, 2023, DOI: 10.1109/ACCESS.2023.3303477.

S. R. Nudin, R. Gernowo, M. Somantri, dan A. Wibowo, “Multi Task Classification using Deep Learning Approaches for Big Five Personality Traits Prediction: A Review,” Proc. - 11th Int. Conf. Inf. Technol. Comput. Electr. Eng. ICITACEE 2024, hal. 37–42, 2024, DOI: 10.1109/ICITACEE62763.2024.10762804.

S. Prasetyo dan T. Dewayanto, “Penerapan Machine Learning, Deep Learning, dan Data Mining dalam Deteksi Kecurangan Laporan Keuangan: Sebuah Kajian Literatur Sistematis,” Diponegoro J. Account., Vol. 13, No. 3, hal. 1–12, 2024, [Daring]. Tersedia pada: http://ejournal-s1.undip.ac.id/index.php/accounting

R. T. Ibrahim dan F. M. Ramo, “Hybrid Intelligent Technique with Deep Learning to Classify Personality Traits,” Int. J. Comput. Digit. Syst., Vol. 13, No. 1, hal. 231–244, 2023, DOI: 10.12785/ijcds/130119.

F. M. Putri, M. I. Ghozali, dan W. H. Sugiharto, “Analisis Komparatif Arsitektur Deep Learning untuk Klasifikasi Citra Rempah - Rempah Indonesia Image Classification,” Sistemasi, Vol. 15, hal. 643–657, 2026.

A. Zada Pramuditha, M. Fadhli, dan Suroso, “Deteksi Wajah dengan Model Arsitektur VGG 19 pada Metode Convolutional Neural Network,” Sist. J. Sist. Inf. , Vol. 13, No. 5, hal. 1998–2007, 2024, [Daring]. Tersedia pada: http://sistemasi.ftik.unisi.ac.id

G. Meena, K. K. Mohbey, A. Indian, dan S. Kumar, “Sentiment Analysis from Images using VGG19 based Transfer Learning Approach,” Procedia Comput. SCI., Vol. 204, No. 2021, hal. 411–418, 2022, DOI: 10.1016/j.procs.2022.08.050.

E. Hassan, M. Y. Shams, N. A. Hikal, dan S. Elmougy, The Effect of Choosing Optimizer Algorithms to Improve Computer Vision Tasks: A Comparative Study, Vol. 82, No. 11. Multimedia Tools and Applications, 2023. DOI: 10.1007/s11042-022-13820-0.

S. Asy Syifa dan I. Amelia Dewi, “MIND (Multimedia Artificial Intelligent Networking Database Arsitektur Resnet-152 dengan Perbandingan Optimizer Adam dan RMSProp untuk mendeteksi Penyakit Paru-Paru,” J. MIND J. | ISSN, Vol. 7, No. 2, hal. 139–150, 2022, [Daring]. Tersedia pada: https://doi.org/10.26760/mindjournal.v7i2.139-150

N. Landro, I. Gallo, dan R. La Grassa, “Mixing ADAM and SGD: A Combined Optimization Method,” 2020, [Daring]. Tersedia pada: http://arxiv.org/abs/2011.08042

S. T. Aung, N. Funabiki, L. H. Aung, S. A. Kinari, M. Mentari, dan K. H. Wai, “A Study of Learning Environment for Initiating Flutter App Development using Docker,” Inf., Vol. 15, No. 4, 2024, DOI: 10.3390/info15040191.

B. S. Puttaswamy dan N. Thillaiarasu, “Fine DenseNet based Human Personality Recognition using English Hand Writing of Non-Native Speakers,” Biomed. Signal Process. Control, Vol. 99, No. August 2024, hal. 106910, 2025, DOI: 10.1016/j.bspc.2024.106910.

S. Checker, M. Yadav, dan R. Katarya, “HiEnWrite: A Hindi-English Bilingual Dataset for Big Five Personality Detection,” ACM Trans. Asian Low-Resource Lang. Inf. Process., Vol. 24, No. 9, hal. 1–19, 2025, DOI: 10.1145/3756010.

A. Remaida dkk., “Application of Artificial Neural Networks for Personality Traits Prediction based on Handwriting,” Indones. J. Electr. Eng. Comput. SCI., Vol. 31, No. 3, hal. 1534–1544, 2023, DOI: 10.11591/ijeecs.v31.i3.pp1534-1544.

A. I. Maulana, C. I. Isniawan, M. Imam, Y. Mustofa, dan P. Pamungkas, “Identifikasi Kepribadian dari Tulisan Tangan menggunakan Euclidean Distance,” Semin. Nas. Teknol. dan Sains, Vol. 2, No. 1, hal. 177–182, 2023.

C. Schröer, F. Kruse, dan J. M. Gómez, “A Systematic Literature Review on Applying CRISP-DM Process Model,” Procedia Comput. SCI., Vol. 181, No. 2019, hal. 526–534, 2021, DOI: 10.1016/j.procs.2021.01.199.

C. J. Soto dan O. P. John, “The Next Big Five Inventory (BFI-2): Developing and Assessing a Hierarchical Model with 15 Facets to Enhance Bandwidth, Fidelity, and Predictive Power,” J. Pers. Soc. Psychol., Vol. 113, No. 1, hal. 117–143, 2017, DOI: 10.1037/pspp0000096.

K. Simonyan dan A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., hal. 1–14, 2015.

M. El Khayati, A. Maafiri, Y. Himeur, H. Ali Alkhazaleh, S. Atalla, dan W. Mansoor, “Leveraging Transfer Learning and Mobile-Enabled Convolutional Neural Networks for Improved Arabic Handwritten Character Recognition,” IEEE Access, Vol. 13, No. September, hal. 166104–166126, 2025, DOI: 10.1109/ACCESS.2025.3613265.

T. Sentoso, F. Ardiansyah, V. Tamuntuan, S. S. Wangsa, K. Kusrini, dan K. Kusnawi, “Identification of Lumpy Skin Disease in Cattle with Image Classification using the Convolutional Neural Network Method,” Sistemasi, Vol. 13, No. 3, hal. 864, 2024, DOI: 10.32520/stmsi.v13i3.2569.

S. W. Sidehabi, A. Suyuti, I. S. Areni, dan I. Nurtanio, “Classification on Passion Fruit’s Ripeness using K-Means Clustering and Artificial Neural Network,” 2018 Int. Conf. Inf. Commun. Technol. ICOIACT 2018, vol. 2018-Janua, hal. 304–309, 2018, DOI: 10.1109/ICOIACT.2018.8350728.

D. Chicco, M. J. Warrens, dan G. Jurman, “The Coefficient of Determination R-Squared is More Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation,” PeerJ Comput. SCI., Vol. 7, hal. 1–24, 2021, DOI: 10.7717/PEERJ-CS.623.

S. N. Papageorgiou, “On Correlation Coefficients and Their Interpretation,” J. Orthod., Vol. 49, No. 3, hal. 359–361, 2022, DOI: 10.1177/14653125221076142.

SQL. Consortium, “Architecture of SQLite.” [Daring]. Tersedia pada: https://sqlite.org/arch.html

M. Sholeh, I. Gisfas, Cahiman, dan M. A. Fauzi, “Black Box Testing on ukmbantul.com Page with Boundary Value Analysis and Equivalence Partitioning Methods,” J. Phys. Conf. Ser., Vol. 1823, No. 1, 2021, DOI: 10.1088/1742-6596/1823/1/012029.




DOI: https://doi.org/10.32520/stmsi.v15i6.6380

Article Metrics

Abstract view : 0 times
PDF - 0 times

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.