Abstract
Learning English pronunciation is crucial in enhancing primary school pupils_ communication skills, yet many struggle. This study evaluates the effectiveness of a natural language processing (NLP) tool in improving primary school pupils_ English pronunciation by measuring motivation, confidence, and performance. Conducted in a primary school in Johor, the research used a randomized controlled trial (RCT) design with 30 Year 3 pupils divided into two groups (15 pupils for each group), which are a control and a treatment group. The English teacher assessed motivation, confidence, and performance using a rubric-based evaluation, with a Cronbach_s Alpha value of 0.932, indicating high reliability. This study compares conventional teaching methods with NLP. With _ = 0.10, multivariate analysis of variance (MANOVA) assessed the effectiveness of the teaching methods. The combined dependent variables significantly differed based on teaching methods, Pillai Trace = 0.95, F (24, 5) = 3.72, p < 0.074, partial __ = 0.95. With _ = 0.05, paired t-tests were conducted to determine whether the two groups' motivation, confidence, and performance differences were statistically significant. For motivation, confidence and performance aspects, the mean differences were significantly different, p-values < 0.05 for the treatment group but not for the control group, p-values > 0.05. The study demonstrates that integrating NLP tools into English pronunciation teaching significantly enhances pupils' motivation, confidence, and performance compared to conventional teaching methods. The use of NLP tools can strengthen personalized learning in learning English pronunciation.