In recent years, there has been a growing interest in the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI) to enhance user experience (UX) through AI-enabled tools. Despite the potential benefits of emerging models and interaction mechanisms, the widespread adoption of such tools remains limited. To address this gap, a systematic literature review was conducted on 359 papers to synthesize the current landscape, identify trends, and uncover unmet needs of UX practitioners in AI support. The analysis, guided by the Double Diamond design framework, revealed that while AI automation can offer efficiency, it may hinder the crucial empathy-building process that is central to UX design. Additionally, focusing solely on individual UI screens without considering interactions and user flows may limit the practical value of AI tools for designers. This highlights the importance of understanding UX practitioners' unique perspectives and incorporating more designer-centric datasets and evaluation metrics in HCI and AI research. Through iterative sampling processes involving backward and forward sampling of relevant papers, a comprehensive dataset was compiled representing existing work in the domain. The analysis categorized papers into phases of the Double Diamond framework, with additional categories for UX-related datasets and general AI models. Each paper was evaluated based on research contribution type, target problem/task addressed, consideration of user needs, empirical evidence from previous work,
AI model architecture and data modality used
important model aspects like user control and explainability
as well as UX artifacts involved. The study identified key aspects for further exploration in AI support for UX design including understanding user needs more deeply within different phases of design processes. The findings underscored the need for a holistic approach that integrates technical feasibility with human-centered design principles to create effective AI tools that truly support UX practitioners. This comprehensive review represents a significant repository of literature on AI for UX support compared to past reviews in this field and sets a foundation for future research collaborations between HCI and AI communities towards enhancing UX through innovative technologies.
- People are interested in combining how humans interact with computers and artificial intelligence to make tools that help us better.
- Not many people are using these AI tools even though they could be really helpful.
- A study looked at a lot of papers to see what's going on with these tools and what designers need.
- The study found that AI might make it hard for computers to understand human feelings, which is important in design.
- It's better to think about how everything works together when designing with AI, not just one screen at a time.
Definitions
- Human-Computer Interaction (HCI): How people use and interact with computers or technology.
- Artificial Intelligence (AI): Machines or computer systems that can learn and solve problems like humans.
- User Experience (UX): How people feel when they use a product or service, especially related to ease of use and enjoyment.
- Automation: Using machines or computers to do tasks automatically without human intervention.
- Empathy: Understanding and sharing the feelings of others.
- Designers: People who create things like websites, apps, or products for others to use.
- Datasets: Collections of data used for analysis or research purposes.
- Evaluation metrics: Standards or criteria used to measure the success or effectiveness of something.
Introduction:
In recent years, there has been a growing interest in the intersection of Human-Computer Interaction (HCI) and Artificial Intelligence (AI) to enhance user experience (UX) through AI-enabled tools. While there is potential for these tools to improve efficiency and effectiveness in UX design, their widespread adoption remains limited. To address this gap, a systematic literature review was conducted on 359 papers to synthesize the current landscape, identify trends, and uncover unmet needs of UX practitioners in AI support.
Methodology:
The study utilized the Double Diamond design framework as a guide for analysis. This framework breaks down the design process into four phases: Discover, Define, Develop, and Deliver. Additionally, categories were created for UX-related datasets and general AI models.
To compile a comprehensive dataset representing existing work in this domain, iterative sampling processes involving backward and forward sampling of relevant papers were conducted. Each paper was evaluated based on research contribution type, target problem/task addressed, consideration of user needs, empirical evidence from previous work,
AI model architecture and data modality used
important model aspects like user control and explainability
as well as UX artifacts involved.
Results:
The analysis categorized papers into different phases of the Double Diamond framework with additional categories for UX-related datasets and general AI models. The results revealed that while AI automation can offer efficiency in certain tasks such as data processing or pattern recognition, it may hinder the crucial empathy-building process that is central to UX design. Additionally, focusing solely on individual UI screens without considering interactions and user flows may limit the practical value of AI tools for designers.
Furthermore, it was found that many studies focused more on technical feasibility rather than human-centered design principles when developing AI tools for UX support. This highlights the importance of understanding UX practitioners' unique perspectives and incorporating more designer-centric datasets and evaluation metrics in HCI and AI research.
Discussion:
The study identified key aspects for further exploration in AI support for UX design, including understanding user needs more deeply within different phases of the design process. This highlights the need for a holistic approach that integrates technical feasibility with human-centered design principles to create effective AI tools that truly support UX practitioners.
The findings also underscored the importance of considering important model aspects such as user control and explainability in AI models for UX support. These factors can greatly impact the usability and acceptance of these tools by designers.
Conclusion:
This comprehensive review represents a significant repository of literature on AI for UX support compared to past reviews in this field. It sets a foundation for future research collaborations between HCI and AI communities towards enhancing UX through innovative technologies. By incorporating human-centered design principles and understanding the unique perspectives of UX practitioners, we can develop more effective AI tools that truly support their work and improve overall user experience.
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.
