An Intelligent Writing Tutor for ESL Learners: A Rule-Based and NLP-Assisted Feedback Framework

Abstract

Writing remains one of the most challenging skills for English as a Second Language (ESL) learners because it requires the coordinated application of grammar, vocabulary, and written discourse conventions. This study proposes an Intelligent Writing Tutor that integrates corpus-informed error analysis, natural language processing (NLP), and rule-based reasoning to generate individualized and explainable writing feedback for ESL learners. Guided by a mixed-methods Design Science Research approach, weekly journal entries produced by Ilocano-speaking English language majors at the Kalinga State University served as the learner corpus for analysis. Manual expert annotation based on Corder's Error Analysis framework identified lexical, morphological, syntactic, and mechanical errors that informed the development of an interpretable rule-based feedback engine. The analysis revealed that morphological errors were the most frequent, followed by mechanical, lexical, and syntactic errors, with verb tense misuse emerging as the dominant writing difficulty. Qualitative findings further indicated that many of the observed errors reflected first-language interference, particularly in tense marking, subject–verb agreement, preposition usage, and lexical choice. The proposed framework operationalizes learner texts through preprocessing, NLP-assisted error detection, rule-based error classification, feedback generation, and recommendation modules to produce individualized feedback reports. The study demonstrates the feasibility of integrating explainable NLP techniques and second language acquisition principles into an educational writing support system. Because the framework was developed using journal writings from Ilocano-speaking learners in a single institution, its applicability to other learner populations requires further investigation.