Hi, I'm Ulia Zaman

Your Name

A bit more about me and what I do.

I'm a second-year PhD student in Computational Media at UC Santa Cruz, where I research games, players, and AI at the Game User Interaction and Intelligence Lab. My work sits at the intersection of human-computer interaction, AI, and education — specifically, how people learn to understand and critically engage with AI-generated content, and how game-based learning environments can support that process. My current dissertation research focuses on AI literacy: examining whether existing frameworks account for generative AI modalities like text, image, and video, and how gameplay mechanics and metacognitive scaffolding shape learners' ability to navigate AI-generated media.

Selected Work

LEAI

2025

Listening with Language Models: Using LLMs to Collect and Interpret Classroom Feedback

LLMs · Conversational AI · Learning analytics

This project explores the use of LLM-powered chatbots as an alternative to traditional end-of-quarter surveys, engaging students in reflective, conversational dialogues mid-course. The result is a three-part system: PromptDesigner, which allows instructors to craft and test course-specific feedback prompts; FeedbackCollector, a student-facing GPT-4 chatbot that elicits detailed, contextual reflections; and FeedbackAnalyzer, a dashboard that synthesizes student responses into actionable insights for instructors. A pilot study across two graduate courses at UC Santa Cruz found that the system surfaced richer, more specific feedback than standard surveys, enabled real-time course adjustments, and was more engaging for students. The project is also investigating the system’s potential for tracking soft skills, including communication, collaboration, goal setting, and conflict resolution, in group work contexts.

Day & Sea project

2024 - 2025

CITRIS - Climate Resilience

Game design · Augmented reality · Climate action

A collaborative research project exploring how serious games can drive environmental action around sea-level rise. The project combined a systematic literature review, a games review using the Wilcox Ladder of Participation framework, and stakeholder interviews to inform the design of Day & Sea – an AR mobile game in which players clean up litter, plant virtual mangroves, and foster coral reefs across three interconnected levels of action: individual, community, and policy. The game was conceptualized through a collaborative gameathon and uses real-world data and gamification to bridge digital interaction and meaningful climate action, with particular attention to communities disproportionately affected by climate change.

Creativity Labs logo

2023

Exploring Computational Thinking Practices and Gestures in the Context of Matrix Math

Interdisciplinary learning activity · Robotics · Embodied cognition

A mixed-methods study examining how interdisciplinary students use gesture and computational thinking practices to make sense of matrix math with a physical robot arm. Video analysis reveals how debugging, abstraction, and bodily imitation of the robot's movement supported learning.

Mario RL agent

2023

Reinforcement Learning Project: Comparing A2C and A3C for Super Mario Bros

Reinforcement learning · Game AI

A comparative study implementing and evaluating Advantage Actor-Critic (A2C) against an existing Asynchronous Advantage Actor-Critic (A3C) model trained to complete Super Mario Bros World 1-1 using OpenAI's gym-super-mario-bros environment. The project involved building an A2C policy gradient from scratch in PyTorch, including custom reward shaping and environment preprocessing, while holding network architecture and training conditions constant to enable a fair comparison. Results revealed a key tradeoff: A2C achieved comparable final performance to A3C but required significantly longer training time, highlighting how parallelized asynchronous updates give A3C its efficiency advantage. The project surfaced practical challenges in deep RL research including dependency management, reward function tuning, and the computational cost of on-policy training.

Let's talk.

Open to new opportunities, collaborations, or just an interesting conversation.

Say hello ↗