NATALIA GULBRANSEN-DIAZ

The future demands hope and imagination. I’m passionate about deploying critical, design-led approaches to address complex social challenges, with particular focus on investigating how we can design with/and/for communities envisioning positive futures.

Through practice-led inquiry and real-world collaborations with Australian NPOs, I work to understand the conditions and relationships that enable design to be generative rather than extractive, bridging theory and application to create responsive, situated engagements that contribute to ongoing conversations about design's role in community and public life.

My recently completed PhD, Design with/and/for Value, explored how design can support non-profit organisations in realising their collective ambitions beyond economic measures.

Email
CV
Publications [Google Scholar]

Research
  1. Design with/and/for Value
  2. Waste to Resilience: Sanitation against Stunting and Climate Vulnerability in Indonesian Informal Coastal Areas [Coming Soon] 
  3. Computational Creativity in the Classroom: Student-Led Co-Design of Generative AI Pedagogies in Design [Coming Soon]
  4. Sonic Street Technologies: Australia
  5. Broadening Horizons: Using Curiosity to Diversify Behaviour
  6. Usability Issues in Self-Service Technologies
  7. COVID-19 Smart IoT Screening System (Pilot) at Sydney Children’s Hospitals Network
  8. Introspect
Broadening Horizons: Using Curiosity to Diversify Behaviour

Research Assistant, 2020–2023
The University of Sydney School of Architecture, Design and Planning (supported by Australian Research Council DECRA fellowship)
[computational creativity] [design and AI]
Publications
Grace, K., Finch, E., Gulbransen-Diaz, N., and Henderson, H. (2022) Q-Chef: The impact of surprise-eliciting systems on food-related decision-making. CHI '22: CHI Conference on Human Factors in Computing Systems.


Can AI-based models of surprise encourage people to try new things? This project investigated whether personalised surprise could diversify diet and evoke curiosity. We developed Q-Chef (the "curious chef"), a mobile app that recommended recipes designed to be both tasty and surprising — comprised of ingredient and flavour combinations each user would find unexpected.

Study flow for the Q-Chef longitudinal deployment: participants completed onboarding surveys, cooked and reviewed meals over four weeks, then participated in post-study interviews.


Two Studies, Evolving Roles


My involvement with Q-Chef grew substantially over three years. I started conducting interviews for the in-lab study, then taught a master's student thematic analysis techniques, and eventually managed the entire four-week longitudinal deployment with 60 participants.

Study 1: In-Lab Testing
Participants used Q-Chef to select a recipe, then I interviewed them about their decision-making process and broader cooking attitudes. Half received recipes that matched their preferences ("tasty"), while half received recipes that were both preference-aligned and predicted to be surprising ("surprising-yet-tasty"). I led thematic analysis with a master's student using investigator triangulation, which revealed five major themes influencing recipe choice: skill inventory, safety in comfort and familiarity, individual decision mentalities, moments of exploration, and social ecology. I contributed to reviewing and writing sections of the resulting CHI paper.

Q-Chef mobile app interface showing the onboarding process, which gathered data on participants' familiarity with and enjoyment of different meals and ingredients.


Study 2: At-Home Deployment
For the four-week in-the-wild study, I transitioned into project management. I liaised with our industry developer on app refinements, conducted usability assessments, and developed participant communication and management protocols that would scale across 60 participants. I supervised two research assistants through participant onboarding, conducted follow-up interviews, led thematic analysis of the qualitative data, and coordinated remuneration distribution throughout the study's duration.

The Tension Between Comfort and Curiosity


Food decisions exist in a constant tension: the comfort and identity of familiar foods versus the allure of new experiences. Our thematic analysis showed that choosing what to cook involves navigating skill level, personal mentalities (health, ethics, practicality), social networks, and immediate constraints like time, cost, and what's already in the fridge.

Surprising recipes shifted this balance. Participants who received "surprising-yet-tasty" recommendations were significantly more likely to reflect enthusiastically on trying new things (p = 0.007), recalling diverse exploratory experiences — new ingredients, unfamiliar preparation methods, novel flavours. The control group's reflections stayed narrowly focused on single dishes. Surprise also made participants significantly more comfortable with the idea of altering familiar dishes (p = 0.024), often attributing this confidence to accumulated cooking knowledge. By contrast, the control group more frequently recalled unsuccessful modification attempts.
Significant differences in how participants in the "surprising-yet-tasty" and "tasty" groups discussed their food decision-making. Codes further from centre showed greater difference between groups.


But surprise came with challenges. Participants receiving unfamiliar recipes were more likely to explicitly consider household preferences when selecting recipes (p = 0.066), suggesting that novel dishes require more deliberate social negotiation. Meanwhile, familiar recipes triggered stronger nostalgic connections to food, culture, and identity (p = 0.089) — a powerful emotional draw that surprise-eliciting systems must contend with. Participants receiving familiar recipes were also more likely to reference well-developed cooking capabilities (p = 0.053), while those in the surprise condition acknowledged skill requirements but felt less confident they possessed them.

Designing for Surprise


The findings pointed to several tensions that future curiosity-eliciting systems need to navigate. Immediate needs (time, available ingredients, cost) often overshadow longer-term goals in food decisions, suggesting that context-aware systems could help users control when and how much they wish to be surprised. Trait curiosity varies significantly between people — some participants embraced novelty enthusiastically while others retreated to the familiar under stress. Systems could use psychometric surveys or learnt "surprise targets" to attenuate novelty levels, preventing overwhelm while still encouraging gradual exploration.

Trusted sources mattered immensely. Participants were far more willing to try new recipes that came from family, friends, or respected food writers. Grounding surprise-eliciting systems in social networks could create a sense of belonging among people exploring new foods together. And finally, predicting what will surprise a specific individual remains technically challenging — our classifiers achieved approximately 70% accuracy, which meant offering users ten recipes to ensure several genuine surprises in the set. Future systems could start with population-level surprise models and gradually personalise as confidence grows.


This work was supported by the Australian Research Council (Project #DE180101416).


©2026 Natalia Gulbransen-Diaz