Data-Driven Hints in Intelligent Tutoring Systems

TL;DR

This paper reviews advancements in data-driven hint generation for intelligent tutoring systems, highlighting techniques like Hint Factory, Interaction Networks, and the integration of Large Language Models to improve hint timing and relevance.

Contribution

It introduces recent developments in data-driven hint generation, including the use of behavioral data and LLMs, advancing personalized and timely support in ITS.

Findings

Data-driven methods enable next-step and strategic hints.

Systems can determine optimal hint timing.

Integration of LLMs enhances hint relevance and adaptability.

Abstract

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).