AI Assistance for UX: A Literature Review Through Human-Centered AI

TL;DR

<3-5 sentence high-level summary> This literature review interrogates how AI can support UX practitioners through a Human-Centered AI lens, organized via the Double Diamond framework. It analyzes 359 papers to reveal a technology-centric bias, uneven coverage across design phases, and a critical gap in empathy-building and cross-screen experiences. The authors argue for designer-centric datasets and UX-focused evaluation metrics, and for closer collaboration between HCI and AI communities to produce practical, user-centered AI tools. The work highlights translational opportunities and offers directional guidance for future research and tool design that truly augments UX practice without eroding designers' empathetic engagement with users.

Abstract

Recent advancements in HCI and AI research attempt to support user experience (UX) practitioners with AI-enabled tools. Despite the potential of emerging models and new interaction mechanisms, mainstream adoption of such tools remains limited. We took the lens of Human-Centered AI and presented a systematic literature review of 359 papers, aiming to synthesize the current landscape, identify trends, and uncover UX practitioners' unmet needs in AI support. Guided by the Double Diamond design framework, our analysis uncovered that UX practitioners' unique focuses on empathy building and experiences across UI screens are often overlooked. Simplistic AI automation can obstruct the valuable empathy-building process. Furthermore, focusing solely on individual UI screens without considering interactions and user flows reduces the system's practical value for UX designers. Based on these findings, we call for a deeper understanding of UX mindsets and more designer-centric datasets and evaluation metrics, for HCI and AI communities to collaboratively work toward effective AI support for UX.

Figures (6)

• Figure 1: Adapted PRISMA statement of our snowball sampling process.
• Figure 2: The Double Diamond design framework, proposed by the Design Council british_design_council_double_nodate.
• Figure 3: Trend of paper counts each year in our sample (the cut-off date of our search is July 2023).
• Figure 4: Trend of the number of papers each year in our sample, for each phase.
• Figure 5: Classification of papers based on their consideration of user needs in each phase of the Double Diamond process. Our classification is based on whether they employed human-centered research methodologies, introduced in previous books and articles olson_ways_2014rosala_discovery_2020farrell_ux_2017rosala_how_2022moran_quantitative_2018, to understand their target user groups.