HelpCoach improves student questions and learning with AI help prompts

HelpCoach: Scaffolding Targeted AI Help-Seeking During Problem-Solving

Human-Computer Interaction

Summary

Students often ask AI for help when solving problems but struggle to ask clear, useful questions. The authors developed HelpCoach, a tool that helps students ask more specific questions by guiding them through the kind of help they need. HelpCoach also gives prompts to improve their question-asking skills while they work. In tests with college students learning programming, HelpCoach led to better questions and more knowledge remembered than just training on how to ask for help before the task.

What this means in practice

Authors

Hyoungwook Jin, Weirui Peng, Jieun Han, Q. Vera Liao, Xu Wang

Abstract

Students increasingly turn to AI for help with problem-solving, yet too much AI support can undermine learning itself. To benefit from AI, students need to specify the necessary knowledge and scaffold type in their questions. However, they struggle to formulate such targeted questions because they lack metacognitive skills to recognize and select effective help options. We developed HelpCoach, an add-on for chat interfaces that helps students formulate knowledge- and scaffold-specific questions and receive targeted help during problem solving. HelpCoach continuously assesses students' help-seeking performance and prompts students to improve through an adaptive revision template. Whereas prior work has largely taught help-seeking skills apart from learning tasks, HelpCoach's in situ scaffold enables concrete practice on metacognitive skills and immediate revisions to help-seeking behavior. In a study with 40 college students learning web programming, HelpCoach led to more specific questions during chatbot interactions and greater knowledge retention than pre-task help-seeking training alone.