A Blended System for Data-Driven Learning of English for Specific Purposes

Abstract

English for Specific Purposes (ESP) and Data-Driven Learning (DDL) are two constructivist and student-centered approaches to language pedagogy that are well-established in second language acquisition. Despite recent fruitful attempts to unify the two approaches for enhanced pedagogical effectiveness, current technological bottlenecks, characterized by a lack of specialized functionality and accessible interfaces for ESP learning, have limited their application in a broader range of scenarios such as blended language learning. To address these issues, the present paper proposes the design and development of a new DDL system tailored to the needs of ESP pedagogy, with functions specifically designed to foster student-centered learning and develop genre awareness at different stages of the ESP learning process. Built on a flexible modular architecture, the system utilizes state-of-the-art techniques in Natural Language Processing (NLP) for efficient multilayered linguistic annotation and indexing, made query-able through a user-friendly web interface that minimizes expertise required for DDL activities. We demonstrate the usefulness of the system with a case study showcasing its key functions for data-driven ESP learning, and discuss its potential use in an integrative blended learning environment