Investigating relationships between reading comprehension and oral reading fluency through AI-driven tool reading progress

Abstract

This study investigates the relationship between reading comprehension and oral reading fluency components—accuracy and rate—among 113 Vietnamese EFL university students using the AI-powered tool Microsoft Reading Progress. Over 14 weeks, students engaged in weekly oral reading and comprehension tasks using integrated Microsoft Teams features. Fluency metrics (accuracy and rate) and comprehension scores were automatically collected and analyzed using Pearson correlation. The results revealed weak but statistically significant positive correlations between reading comprehension and accuracy (r = .257, p < .01), and between comprehension and rate (r = .289, p < .01), suggesting that improvements in fluency modestly support comprehension. A strong correlation between accuracy and rate (r = .765, p < .01) was also observed. The study highlights the effectiveness of Reading Progress in capturing fluency data and promoting self-paced improvement. However, limitations such as the short duration, localized sample, and constraints of accent recognition in AI-based speech analysis affect the generalizability and validity of results. The findings support the pedagogical integration of AI tools in EFL instruction while calling for future research with larger samples, extended timelines, and diversified digital tools to further validate and expand on these results.