Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload

TL;DR

This paper presents VisDoc, a GenAI-powered tool that restructures open source onboarding docs using Cognitive Theory of Multimedia Learning, reducing cognitive load and enhancing usability for newcomers.

Contribution

It introduces a CTML-based analysis, a GenAI pipeline for restructuring documentation, and provides empirical evidence of improved onboarding outcomes.

Findings

VisDoc achieves higher task success rates.

Participants report lower cognitive load with VisDoc.

Expert evaluation confirms VisDoc's accuracy and adoptability.

Abstract

Onboarding documentation is critical for attracting and retaining newcomers in open source software (OSS). However, it is often presented as dense, inconsistently structured, and fragmented presentations that are difficult to understand, which creates cognitive overload leading to frustration, errors, and abandonment. Here, we investigate how Cognitive Theory of Multimedia Learning (CTML) strategies can be used to restructure OSS documentation. We use a GenAI-based pipeline to operationalize these strategies to restructure OSS documentation through our prototype VisDoc. VisDoc segments documentation into task-based units, infers workflows, removes redundancy, and generates multimodal explanations. An expert evaluation (N=4) affirmed VisDoc's completeness, accuracy, and adoptability; A between-subjects evaluation (N=14) with newcomers found that VisDoc participants achieved higher task success, had significantly lower cognitive load, and perceived higher usability. The contributions of this work include a CTML-grounded analysis of onboarding challenges, a GenAI-based documentation restructuring pipeline, and empirical evidence that cognitively informed documentation restructuring reduces cognitive load and improves usability and task performance in OSS.