Data-driven learning and artificial intelligence: a comparison between two approaches to the creation of language teaching materials

This dissertation explores the efficacy of two distinct methodologies, data-driven learning (DDL) and artificial intelligence (AI), in the development of language teaching materials. Drawing from the fields of linguistics, education, and computer science, the study investigates the extent to which these approaches enhance language acquisition and pedagogical effectiveness. A comprehensive review of the literature examines the theoretical and practical implications of using Data-Driven Learning (DDL) and Artificial Intelligence (AI) in language education. DDL stresses the significance of incorporating authentic language data to develop instructional content that is applicable and enhances learner self-direction. In contrast, AI employs sophisticated machine learning algorithms to dynamically generate and tailor learning materials according to the unique needs and preferences of each student. This thesis delves into a comparative analysis of two pairs of exercises, scrutinizing their respective presentation techniques, problem-solving methodologies, and overall effectiveness in promoting student learning. The results show that both exercises have their strengths and weaknesses. Nevertheless, this study requires further insights and practical experiments to better and more accurately evaluate artificial intelligence and DDL in making exercises for language learners.

This dissertation explores the efficacy of two distinct methodologies, data-driven learning (DDL) and artificial intelligence (AI), in the development of language teaching materials. Drawing from the fields of linguistics, education, and computer science, the study investigates the extent to which these approaches enhance language acquisition and pedagogical effectiveness. A comprehensive review of the literature examines the theoretical and practical implications of using Data-Driven Learning (DDL) and Artificial Intelligence (AI) in language education. DDL stresses the significance of incorporating authentic language data to develop instructional content that is applicable and enhances learner self-direction. In contrast, AI employs sophisticated machine learning algorithms to dynamically generate and tailor learning materials according to the unique needs and preferences of each student. This research delves into a comparative analysis of two pairs of exercises, scrutinizing their respective presentation techniques, problem-solving methodologies, and overall effectiveness in promoting student learning. The results show that both exercises have their strengths and weaknesses. Nevertheless, this study requires further insights and practical experiments to better and more accurately evaluate artificial intelligence and DDL in making exercises for language learners.