Machine learning approach to analyze the impact of demographic and linguistic features of children on their stuttering

Abstract

This study aims at analyzing the impact of gender and race on the linguistic abilities and stuttering of children. The current article also seeks to check whether children with stuttering disorder and normal children differ in linguistic skills. Parametric methods like t-tests and Analysis of Variance (ANOVA) have been applied to test hypotheses. The p-values that were generated in the parametric tests signify that the gender of the child has an impact on the onset of stuttering. However, the race of children did not affect the onset of stuttering. The regression results of the machine learning part have indicated many findings. The results indicated that a child’s race does not impact the onset of stuttering. Hence, the null hypothesis about race was accepted by signifying that children of any race can adopt stuttering. This finding also suggests that children can face linguistic difficulties irrespective of their race. Another finding is that children with stuttering (CWS) repeat more words than children with not stuttering (CWNS). In addition, CWS repeat more syllables than CWNS. It indicates that the null hypothesis can be accepted by stating that children can suffer from linguistic difficulties irrespective of their race. Another key finding is that there can be a significant difference in the linguistic abilities of male and female children. Another inference is that the p-values indicate a significant difference between linguistic skills among CWS and CWNS. In other words, CWS are more prone to repeat syllables than normal children.