AI-Driven Practical English Textbooks: A Five-Layer Architecture and Eight-Week Classroom Study

Forum topic · 小凯 · 2026-09-06

Summary

This paper presents the structure and implementation of a new practical English textbook driven by artificial intelligence, authored by Ya Wang, Lei Zhang, and Xueguang Yang (arXiv:2509.00001). The work proposes a five-layer architecture consisting of knowledge mapping, learner profiling, task generation, feedback orchestration, and teacher-side governance, transforming fixed paper-based materials into adaptive learning systems that diagnose learners, recommend tasks, and provide formative feedback. A prototype was evaluated with 186 non-English-major undergraduates over eight weeks of instruction. Compared with a static digital textbook, the AI-driven system improved unit completion accuracy from 72.4% to 84.9%, raised the average speaking task score by 10.8 points, and reduced teacher correction time by 31.6%. The results indicate that AI-powered textbooks can deliver personalized learning paths, richer exercise content, and traceable classroom data while maintaining curricular stability.

Paper Overview

Research Area: AI/ML Authors: Ya Wang, Lei Zhang, Xueguang Yang Published: 2026-09-06 arXiv: 2509.00001

Abstract

Artificial intelligence is changing the form of applied English materials from fixed paper sequences to adaptive learning systems that can diagnose learners, recommend tasks, and provide formative feedback. This paper studies the structure and application of a new practical English textbook driven by artificial intelligence. A five-layer architecture is proposed: knowledge mapping, learner profiling, task generation, feedback orchestration, and teacher-side governance. A prototype was tested on 186 non-English-major undergraduates for eight weeks of teaching. Compared with a static digital textbook, the proposed system increased the unit completion accuracy from 72.4% to 84.9%, raised the average score for speaking tasks by 10.8 points, and reduced the teacher's correction time by 31.6%. The findings suggest that AI-driven textbooks can provide personalized learning paths, enriched exercise materials, and traceable classroom data while maintaining curricular stability.

Key Contributions

A five-layer architecture for AI-driven English textbooks: knowledge mapping, learner profiling, task generation, feedback orchestration, and teacher-side governance
An eight-week classroom evaluation with 186 non-English-major undergraduates
Measured improvements over a static digital textbook:
Unit completion accuracy: 72.4% → 84.9%
Average speaking task score: +10.8 points
Teacher correction time: −31.6%

Significance

The study demonstrates that AI-driven textbooks can balance adaptivity with curricular stability, offering individualized learning paths and actionable, traceable classroom analytics for teachers.