Identification and characterization of learning weakness from drawing analysis at the pre-literacy stage

Abstract

Handwriting learning delays should be addressed early to prevent their exacerbation and long-lasting consequences on whole children’s lives. Ideally, proper training should start even before learning how to write. This work presents a novel method to disclose potential handwriting problems, from a pre-literacy stage, based on drawings instead of words production analysis. Two hundred forty-one kindergartners drew on a tablet, and we computed features known to be distinctive of poor handwriting from symbols drawings. We verified that abnormal features patterns reflected abnormal drawings, and found correspondence in experts’ evaluation of the potential risk of developing a learning delay in the graphical sphere. A machine learning model was able to discriminate with 0.75 sensitivity and 0.76 specificity children at risk. Finally, we explained why children were considered at risk by the algorithms to inform teachers on the specific weaknesses that need training. Thanks to this system, early intervention to train specific learning delays will be finally possible.

Deep Learning and Procrustes Analysis for Early Dysgraphia Risk Detection with a Tablet Application

“…In detail, the two vectors of the latent representation, i.e., pulsations and phases with i = 1, …, s , and the vector of weights of the decoder’s layer, representing the importance of each of the sinusoids found by the network, i.e., with i = 1, …, s . Since the most discriminative features for the identification of handwriting difficulties are those related to frequency [ 11 ], the linear component of Time2Vec, i.e., the component corresponding to i = 0, was excluded from the extracted feature set and used only at the reconstruction stage.…”

“…Recently, Dui et al [ 11 ] confirmed the effectiveness of deep learning in the context of dysgraphia prevention even before handwriting is learned. Using serious games from the iPad application Play-Draw-Write, the authors collected data from children in the last year of kindergarten, and through the use of a convolutional neural network called LearNet, they were able to effectively discriminate between “at-risk” and “non-at-risk” children.…”

“… The necessity to depend only on handwritten text, and thus without providing a quantitative assessment of gestural production [ 10 ]. The requirement for children to reach the clinicians’ office, which may not be easily accessible in terms of costs and waiting time [ 11 ]. …”

“…The requirement for children to reach the clinicians’ office, which may not be easily accessible in terms of costs and waiting time [ 11 ].…”

On the Need for Accurate Brushstroke Segmentation of Tablet-Acquired Kinematic and Pressure Data: The Case of Unconstrained Tracing

“…The emergence of affordable digital tablets over the past decade has created new opportunities for identifying cognitive and motor control differences among populations through drawing, tracing, and handwriting tasks [1][2][3][4][5][6][7][8][9][10][11][12]. Compared to conventional penand-paper assessments, which limit analysis to the final product, tablet computers allow researchers to study the process of drawing by capturing continuous changes in pen position, pen-on-tablet pressure, and the stylus azimuth or tilt.…”