Did AI-generated visual explanations help students with dyslexia understand what they read?

Details

Students with learning disabilities, particularly dyslexia, often have reading-comprehension difficulties that traditional instruction may not fully address. Generative artificial intelligence (GenAI) offers emerging opportunities for personalised, visual instructional support. The study investigated whether GenAI-based visual instruction could support reading comprehension in students with dyslexia.

Researchers used a single-case experimental design with a multiple-probe across participants approach. The participants were three male students aged 9–11 diagnosed with dyslexia, all attending a public elementary school in Yanbu city, Saudi Arabia. The intervention used ChatGPT-generated visual explanations aligned with the Grade 4 Arabic language coursebook. Five-point quizzes assessed the students’ comprehension of paragraphs taken from the Arabic language coursebook.

All three began with a low, stable baseline of 0%–10%. Mastery during treatment was defined as scoring at least 80% in three consecutive assessment sessions. Using this criterion, two participants showed immediate level changes, while the third showed a clear accelerating trend. In maintenance probes several weeks after the intervention ended, all three sustained performance at or above mastery.

Visual analysis indicated a strong functional relation, minimal or no phase overlap, and durable effects. The findings provide preliminary evidence that GenAI-enhanced visual instructional tools can support reading comprehension in students with dyslexia.