Skip to content
Open access

Can AI make reading more engaging? A motivational framework for AI-assisted reading assessment in EFL/ESL classrooms: a practitioner case study

Oct 2026 · Frontiers in Education · 0 citations · 27 references

Abstract

Sustaining reading motivation in EFL and ESL settings remains a persistent pedagogical challenge. Textbook-based comprehension tasks—with predictable content, pre-printed answer keys, and limited interactivity—can produce passive compliance rather than engagement. The maturation of large-language-model (LLM) tools now makes it feasible for individual practitioners to generate demographically responsive, proficiency-calibrated reading materials at low time cost. This paper introduces the AI-Mediated Motivational Reading Assessment (AMMA) framework: a practitioner-developed instructional model grounded in four motivational conditions—interest, achievement, practice, and focused attention—operationalized through a six-stage workflow combining AI text and MCQ generation, session-adaptive item loading, student-autonomous submission, optical-mark-recognition (OMR) grading, and same-session LMS feedback. The paper's primary contribution is the framework itself; the accompanying data are illustrative rather than evaluative. The framework was implemented across six MCQ reading quizzes administered to 53 EFL university students (Section 1: n  = 33; Section 2: n  = 20) over one semester. Quiz 1 used a textbook passage; Quizzes 2–6 used AI-generated passages. Quizzes 1–3 were delivered online and unproctored; Quizzes 4–6 were paper-based and invigilated. The design is a single-cohort descriptive case study with no control group. Passage source is fully confounded with delivery modality, quiz sequence, and cumulative exposure; no inferential tests were conducted. Mean scores were 8.4 percentage points higher on AI-generated quizzes than on the textbook quiz (77.8% vs. 69.4%), with narrower dispersion (SD 19.8 vs. 25.1). Because of the confounding noted above, this difference cannot be attributed to passage source. Online quizzes exceeded paper-based quizzes by 5.3 points overall and by approximately 10 points when the textbook quiz is excluded; since online delivery was unproctored, the paper-based scores are the more defensible estimate of independent reading comprehension. Instructor observations recorded peer discussion of quiz content, grade anticipation, and one unsolicited positive evaluation. These observations were not systematically coded and were recorded by the framework's designer. The AMMA framework offers a practical, low-cost, replicable workflow for high-frequency formative reading assessment, and its logistical viability was demonstrated across six cycles. The data reported here are consistent with, but do not establish, a motivational or comprehension benefit. Controlled evaluation with validated motivational instruments, counterbalanced modality, and independent observation is required before effectiveness claims can be sustained.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.