Abstract
Handwriting is an expressive behavior and communicates one’s personality characteristics. In this work, we try to build a correlation between personality traits and handwriting features employing machine learning techniques. Quantitative analysis is done for correlating handwritten features and personality traits. Two datasets are created for the work, personality trait value dataset and handwriting feature value dataset. The Big Five personality assessment model along with BFI questionnaire are used to collect personality data. It is observed that in handwriting samples of a person, there is a consistency of certain features in respect of graphometric measurements which are both repeatable and reliable. We utilize the measurements related to four lowercase letters of English handwritten script, namely ‘a’, ‘g’, ‘n’ and ‘t’, and the features of the word ‘of’ as well. Personality trait prediction from handwriting features is formulated as a multi-label classification problem. Each of the five traits corresponds to a class in the classifier. Both non-binary and binary label values are examined by using three multi-label classifiers, Classifier Chain (CC), Binary Relevance (BR) and Label-Power set (LP). We employ KSTAR, K-nearest neighbor and Multi-layer Perceptron (MLP) as base classifiers. CC-KSTAR (94.1% with non-binary label values) and CC/LP-KSTAR (97.6% with binary label values) provide the best result considering train-test (67:33) as test option. CC-KNN (ED) (98.1% with non-binary label values) displays the best result considering cross validation as a test option.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hall CS, Lindzey G, Campbell JB (2020) Theories of personality. Wiley, Berlin
Friedman HS, Schustack MW (2009) Personality: classic theories and modern research. Pearson Education, New Delhi
Rothmann S, Elize C (2003) The big five personality dimensions and job performance. South Afr J Ind Psychol 29:68–74
Corr PJ, Matthews G (2009) The Cambridge handbook of personality psychology. Cambridge University Press, Cambridge
Plamondon R (2010) Neuromuscular studies of handwriting generation and representation. In: International conference on frontiers in handwriting recognition (ICFHR), Kolkata, India
Galbraith D, Wilson W (1964) Reliability of the graphoanalytic approach to handwriting analysis. Perceptual Motor Skills 19:615–618
Sheikholeslami G, Srihari SN, Govindaraju V (1996) Computer aided graphology. In: International workshop on frontiers in handwriting recognition, England, pp 457–460
Kedar S, Nair V, Kulkarni S (2015) Personality identification through handwriting analysis: a review. J Adv Res Comput Sci Softw Eng 5(1)
Gavrilescu M (2017) 3-layer architecture for determining the personality type from handwriting analysis by combining neural networks and support vector machines. Electr Eng Comp Sci 79:135–152
Ghosh S, Shivakumara P, Roy P, Pal U, Lu T (2020) Graphology based handwritten character analysis for human behavior identification. CAAI Trans Intell Technol
Tett RP, Palmer CA (1997) The validity of handwriting elements in relation to self-report personality trait measures. Personal Ind Diff 22:11–18
Meka:a multi-label extension to weka (2018). https://sourceforge.net/projects/meka/files/Datasets. Accessed 9 Oct 2020
Srihari SN, Cha SH, Arora H, Lee S (2002) Individuality of handwriting. J Foren Sci 47(4)
Pervouchine V, Leedham G (2007) Extraction and analysis of forensic document examiner features used for writer identification. Pattern Recogn 40(03):1004–1013
Srihari SN, Meng L, Hanson L (2016) Development of individuality in children’s handwriting. J Forens Sci 61(5):1292–1300
Rachmawanto EH, Anarqi GR, Setiadi DRIM, Sari CA (2018) Handwriting recognition using eccentricity and metric feature extraction based on k-nearest neighbors. In: 2018 international seminar on application for technology of information and communication, pp 411–416
Sharma MK, Chanderiya V (2020) Writer identification using graphemes. Indian Academy of Sciences
Mukherjee S, Ghosh ID (2020) Writer identification based on writing individuality and combination of features. In: 2nd international conference on applied signal processing
Coll R, Fornes A, Llados J (2009) Graphological analysis of handwritten text documents for human resources recruitment. In: 10th international conference on document analysis and recognition, pp 1081–1085
Prasad S, Singh VK, Sapre A (2010) Handwriting analysis based on segmentation method for prediction of human personality using support vector machine. Int J Comput Appl 08(12):0975–8887
Champa HN, AnandaKumar KR (2010) Automated human behavior prediction through handwriting analysis. In: 2010 first international conference on integrated intelligent computing, pp 160–165
Rahiman A, Varghese D, Kumar M (2013) Handwritten analysis based individualistic traits prediction. Int J Image Proc 07(2):209–218
Joshi P, Agarwal A, Dhavale A, Suryavanshi R (2015) Handwriting analysis for detection of personality traits using machine learning approach. Int J Comput Appl 130(15)
Tarare PR, Jadhav D (2015) Study of personality prediction based on handwriting and signature recognition using multiple artificial neural network and multi-structure algorithm. Int J Pure Appl Res Eng Technol 3(9):681–693
Manimala S, Gopal M, Gokhale PG, Chandrashekar S (2016) Automated handwriting analysis for human behavior prediction. Int J Comput Sci Eng 5(5):7–14
Garoot AH, Safar M, Suen CY (2017) A comprehensive survey on handwriting and computerized graphology. In: 14th IAPR international conference on document analysis and recognition (ICDAR), vol 01, pp 621–626
Bhade V, Baraskar T (2018) A model for determining personality by analyzing off-line handwriting. Springer, Singapore
Lemos N, Shah K, Rade R, Shah D (2018) Personality prediction based on handwriting using machine learning. In: International conference on computational techniques, electronics and mechanical systems (CTEMS), pp 110–113
Fallah B, Khotanlou H (2016) Identify human personality parameters based on handwriting using neural network. In: Artificial intelligence and robotics, pp 120–126
Dengfeng W, Hong C (2003) Processes and preliminary results in the construction of the chinese personality scale (qzps). J Chinese Psychol Acta Psychol Sinica 35:127–136
Chen Z, Lin T (2017) Automatic personality identification using writing behaviours: an exploratory study. Behav Inf Technol 1–8
Gavrilescu M (2015) Study on determining the myers-briggs personality type based on individual’s handwriting
Gavrilescu M, Vizireanu N (2018) Predicting the big five personality traits from handwriting. EURASIP J Image Video Proc 57:1–17
Lima ACE, de Castro LN (2014) A multi-label, semi-supervised classification approach applied to personality prediction in social media. Neural Netw 58:122–130
Modi H, Panchal M (2012) Experimental comparison of different problem transformation methods for multi-label classification using meka. Int J Comput Appl 59(15):0975–8887
Pushpa M, Karpagavalli S (2017) Multi-label classification: problem transformation methods in tamil phoneme classification. In: 7th international conference on advances in computing and communications, Cochin, pp 572–579
Charte F (2020) A comprehensive and didactic review on multilabel learning software tools. IEEE Access 8:50330–50354
Goldberg LR (2006) An alternative “description of personality’’: the big-five factor structure. J Personal Soc Psychol 59(6):1216–1229
Costa P, McCrae R (1992) Normal personality assessment in clinical practice: the neo personality inventory. Psychol Ass 4:5–13
John O, Naumann LP, Soto CJ (2008) Handbook of personality: Theory and research, 3rd edn. Guilford Press, University of California at Berkeley
Goldberg L, Johnson J, Eber HW, Hogan R, Ashton MC, Cloninger R, Gough HG (2006) The international personality item pool and the future of public-domain personality measures. J Res Personal 40:84–96
Cherman EA, Monard MC, Metz J (2011) Multi-label problem transformation methods: a case study. CLEI Electron J 14(1)
Multi-label classification with scikit-multilearn (2018). https://xang1234.github.io/multi-label. Accessed 08 Oct 2020
Multi-label classification (2015). https://users.ics.aalto.fi/jesse/. Accessed Jan 2021
Srihari SN, Cha SH, Arora H, Lee S (2001) Individuality of handwriting: a validation study. In: 6th international conference on document analysis and recognition
Skills for action. https://skillsforaction.com. Accessed 11 oct 2020
Ratha NK, Govindaraju V (2008) Advances in biometrics sensors, algorithms and systems. Springer, London
Mahanta LB, Deka A (2013) Skew and slant angles of handwritten signature. Int J Innov Res Comput Commun Eng 1(9)
Read J, Reutemann P, Pfahringer B, Holmes G (2016) Meka: a multi-label/multi-target extension to weka. J Mach Learn Res 17:1–5
Acknowledgements
We express our gratitude to Prof. Kaushik Roy of West Bengal State University, Barasat, India, for guiding us to get the ethical clearance for our work.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mukherjee, S., Ghosh, I.D., Mukherjee, D. (2022). Big Five Personality Prediction from Handwritten Character Features and Word ‘of’ Using Multi-label Classification. In: Giri, D., Raymond Choo, KK., Ponnusamy, S., Meng, W., Akleylek, S., Prasad Maity, S. (eds) Proceedings of the Seventh International Conference on Mathematics and Computing . Advances in Intelligent Systems and Computing, vol 1412. Springer, Singapore. https://doi.org/10.1007/978-981-16-6890-6_21
Download citation
DOI: https://doi.org/10.1007/978-981-16-6890-6_21
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6889-0
Online ISBN: 978-981-16-6890-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)