Speaker
Description
While digital higher education collects vast amounts of student data, learning analytics tools rarely translate these metrics into actionable teaching strategies. Traditional platforms rely on static dashboards for passive tracking, leaving language learners to navigate digital resources without personalized guidance. To bridge this gap, this study evaluates Cognilearn, an adaptive intelligent tutoring system designed to guide students through personalized language learning pathways. The research analyzes authentic classroom data, including student test submissions and interaction logs, to build precise profiles of individual learner strengths and language gaps. Instead of immediately providing answers, the system uses real-time guided prompts to encourage active reasoning and student self-correction. This study offers key contributions to the TESOL discipline by demonstrating how intelligent tutoring systems can transcend basic conversational chatbots to provide structured, pedagogically sound language support. Specifically, it proves how data-driven learner modeling can dynamically align language assessment, curriculum progression, and real-time scaffolding. For TESOL educators, this provides a scalable framework to target individual linguistic weaknesses and foster autonomous second language acquisition in digital environments.
