Table of Contents
Fetching ...

AI-Assisted Causal Pathway Diagram for Human-Centered Design

Ruican Zhong, Donghoon Shin, Rosemary Meza, Predrag Klasnja, Lucas Colusso, Gary Hsieh

TL;DR

This work investigates incorporating Causal Pathway Diagrams (CPD) into early-stage human-centered design and delivers a Miro-based CPD plugin with AI-assisted guidance. It demonstrates that CPD supports goal-oriented ideation, constraint identification, strategic prioritization, and cross-stakeholder communication, while reducing cognitive load. The plugin, powered by an LLM, increases idea diversity and helps articulate concepts, though designers call for better context-specific guidance and provenance for AI recommendations. Overall, the study highlights the potential of AI-assisted CPDs to promote evidence-based creativity in design, while underscoring the need for responsibly integrating AI and user-research provenance into practice.

Abstract

This paper explores the integration of causal pathway diagrams (CPD) into human-centered design (HCD), investigating how these diagrams can enhance the early stages of the design process. A dedicated CPD plugin for the online collaborative whiteboard platform Miro was developed to streamline diagram creation and offer real-time AI-driven guidance. Through a user study with designers (N=20), we found that CPD's branching and its emphasis on causal connections supported both divergent and convergent processes during design. CPD can also facilitate communication among stakeholders. Additionally, we found our plugin significantly reduces designers' cognitive workload and increases their creativity during brainstorming, highlighting the implications of AI-assisted tools in supporting creative work and evidence-based designs.

AI-Assisted Causal Pathway Diagram for Human-Centered Design

TL;DR

This work investigates incorporating Causal Pathway Diagrams (CPD) into early-stage human-centered design and delivers a Miro-based CPD plugin with AI-assisted guidance. It demonstrates that CPD supports goal-oriented ideation, constraint identification, strategic prioritization, and cross-stakeholder communication, while reducing cognitive load. The plugin, powered by an LLM, increases idea diversity and helps articulate concepts, though designers call for better context-specific guidance and provenance for AI recommendations. Overall, the study highlights the potential of AI-assisted CPDs to promote evidence-based creativity in design, while underscoring the need for responsibly integrating AI and user-research provenance into practice.

Abstract

This paper explores the integration of causal pathway diagrams (CPD) into human-centered design (HCD), investigating how these diagrams can enhance the early stages of the design process. A dedicated CPD plugin for the online collaborative whiteboard platform Miro was developed to streamline diagram creation and offer real-time AI-driven guidance. Through a user study with designers (N=20), we found that CPD's branching and its emphasis on causal connections supported both divergent and convergent processes during design. CPD can also facilitate communication among stakeholders. Additionally, we found our plugin significantly reduces designers' cognitive workload and increases their creativity during brainstorming, highlighting the implications of AI-assisted tools in supporting creative work and evidence-based designs.
Paper Structure (47 sections, 8 figures, 1 table)

This paper contains 47 sections, 8 figures, 1 table.

Figures (8)

  • Figure 1: An example of causal pathway diagram of increasing clients' physical activities
  • Figure 2: Key screens of our plugin. Consisting of five features, the plugin streamlines the creation and validation of CPD
  • Figure 3: An example design sprint
  • Figure 4: Quantitative results of our user study. Bars indicate standard errors (*: $p<.05$, **: $p<.01$)
  • Figure 5: Sample CPDs generated during the design sprints by participants to address the prompt shown in \ref{['fig:designsprint']}
  • ...and 3 more figures