(Swiss) GraphoLearn: an app-based tool to support beginning readers

Abstract

We assessed the Swiss-German version of GraphoLearn, a computer game designed to support reading by training grapheme-phoneme correspondences. A group of 34 children at risk for dyslexia trained three times a week during 14 weeks, on top of their standard school instruction. The sample was divided into two groups of 18 and 16 children, who started training at either the middle or the end of first grade. We found beneficial training effects in pseudoword reading in both training groups and for rapid automatized naming skills in the group that trained earlier. Our results suggest that both the efficiency in phonological decoding and rapid access to verbal representations are susceptible to facilitation by GraphoLearn. These findings confirm the utility of the training software as a tool to support school instruction and reading-related abilities in beginning readers. We discuss ideas to improve the content and outcomes of future versions of the training software.

Keywords: Beginning readers; Children at risk for developmental dyslexia; Computer-based training; Grapheme-phoneme learning; GraphoLearn.

Fig. 1

Results for the SLRT-II pseudoword reading task. a Line plots show individual scores and group means across the 3-time points for group 1 (top) and group 2 (bottom). The training period for each group is indicated by a yellow bar in the x-axis. Dashed lines indicate children for which the data of one test time was missing, error bars indicate SEM and asterisks indicate significant t tests at pcorr < 0.05. b Violin and box plots show delta scores for each group during the training period (left) and waiting control period (right). Black horizontal bar indicates the median. Data from group 1 are shown in red and data from group 2 in blue

Fig. 2

Group means in each time point for RAN subtasks. Error bars represent SEM. Data from group 1 are shown in red and data from group 2 in blue. Effects of the t tests between each pair of time points are indicated by asterisks (p_corr < 0.05) and daggers (p_corr < 0.1)