Integrating Corpus-Based Translation, Data-Driven Learning, and Generative AI for Professional Email Writing in ESP

Professional communication in English has become increasingly important for librarians participating in international academic and institutional networks. However, many librarians and students have limited English proficiency and need support to write appropriate professional messages. This paper proposes and analyses a didactic sequence designed to help (future) librarians develop professional email writing skills, with a focus on genre awareness and task-specific vocabulary. The sequence emphasises interactional processes central to Data-driven Learning (DDL). Learner–corpus interactions involve building and exploring bilingual email corpora with generative Artificial Intelligence (AI) support, using concordance tools and query logs to identify recurring language patterns and genre conventions. Learner–AI interactions occur as participants use prompts, receive automated feedback, and compare AI-generated suggestions with their own drafts to refine accuracy and register. Peer–peer interactions are fostered through collaborative drafting and discussion activities. The study is framed by DDL and AI, Translation Studies and English for Specific Purposes. Implemented in a Librarianship course at a Brazilian public university, the sequence supported the development of genre-aware professional email writing while fostering transferable corpus-informed and AI-mediated writing strategies to new professional communication contexts.