A Taxonomy of Errors in English as she is spoke: Toward an AI-Based Method of Error Analysis for EFL Writing Instruction

TL;DR

This paper presents an AI-based system utilizing large language models to classify, analyze, and provide feedback on English writing errors in EFL contexts, aiming to enhance language instruction.

Contribution

It introduces a detailed, linguistically grounded taxonomy integrated with AI to automate error analysis in EFL writing instruction, improving granularity and feedback quality.

Findings

Successfully identified diverse error types in authentic texts

Demonstrated potential for automating detailed error feedback

Faced challenges with contextual understanding and uncoded errors

Abstract

This study describes the development of an AI-assisted error analysis system designed to identify, categorize, and correct writing errors in English. Utilizing Large Language Models (LLMs) like Claude 3.5 Sonnet and DeepSeek R1, the system employs a detailed taxonomy grounded in linguistic theories from Corder (1967), Richards (1971), and James (1998). Errors are classified at both word and sentence levels, covering spelling, grammar, and punctuation. Implemented through Python-coded API calls, the system provides granular feedback beyond traditional rubric-based assessments. Initial testing on isolated errors refined the taxonomy, addressing challenges like overlapping categories. Final testing used "English as she is spoke" by Jose da Fonseca (1855), a text rich with authentic linguistic errors, to evaluate the system's capacity for handling complex, multi-layered analysis. The AI successfully identified diverse error types but showed limitations in contextual understanding and occasionally generated new error categories when encountering uncoded errors. This research demonstrates AI's potential to transform EFL instruction by automating detailed error analysis and feedback. While promising, further development is needed to improve contextual accuracy and expand the taxonomy to stylistic and discourse-level errors.