Data-Driven Hints in Intelligent Tutoring Systems
This work is relevant for researchers and developers of intelligent tutoring systems seeking to improve the effectiveness and timing of hints for students.
This chapter reviews the development of data-driven hint generation in intelligent tutoring systems, focusing on techniques like the Hint Factory and Interaction Networks that generate next-step hints, waypoints, and strategic subgoals from student data. It also discusses methods for determining optimal hint timing and explores future adaptations using behavioral data and Large Language Models.
This chapter explores the evolution of data-driven hint generation for intelligent tutoring systems (ITS). The Hint Factory and Interaction Networks have enabled the generation of next-step hints, waypoints, and strategic subgoals from historical student data. Data-driven techniques have also enabled systems to find the right time to provide hints. We explore further potential data-driven adaptations for problem solving based on behavioral problem solving data and the integration of Large Language Models (LLMs).