Case Study 3 | UX Portfolio

Overview

As part of my Master's degree in Human-Computer Interaction (HCI), I took on this project for my dissertation. This topic resonated with me after working as a Research Assistant at the university, which inspired me to delve deeper into the challenges students encounter in their communication and interaction with the university.

Over the course of this three-month research venture, I had the opportunity to refine my skills in areas such as qualitative research, user research, user experience design, data collection and analysis, utilizing Figma, conducting expert evaluation testing, and, of course, effective communication.

Background & Motivation

University student support services play a pivotal role in students' performance and success. Timely, accurate information and personalized assistance are critical.

Communication gaps and lack of student support pose issues such as:

Student Frustration

Students often experience dissatisfaction and frustration due to slow or ineffective support (Santoso, 2018; Waddington, 2010; Ranoliya, 2017).

Negative Perception

Disconnection from the university community and a lack of trust in the institution's responsiveness (Gray, 2021).

Information Gaps

Fragmented sources lead to students missing out on critical updates and services (Waddington, 2010).

Definitions & Research Questions

"Communication" in this context:

Refers to both academic and non-academic matters, including but not limited to:

Access to course and student support service information
Well-being support
Financial assistance
Application guidance
Educational support
Other student inquiries

Why GPT?

Enhances efficiency and efficacy (Rasul, 2023)
Streamlines tasks, saves time and cost (Rasul, 2023; Merelo, 2022)
Reduces staff workload, enhances student engagement (Santoso, 2018)

Research Questions

What are the specific communication challenges faced by staff and students in universities?
How can GPT-based systems be designed to address those challenges effectively, and what are some of the benefits and drawbacks?
What are the key features that contribute to successful adoption of GPT-based systems in universities?

Research & Design Process

Overview

This project followed a multi-phase HCI research approach, blending qualitative insights with co-design and expert feedback. With a timeline of under three months, each phase built upon the last—ensuring that the final solution was both user-centered and technically grounded.

Below is an overview of the research process.

Phase 1: Semi-Structured Interviews

Qualitative interviews were conducted with 2 students and 1 staff member. Each 45–60-minute session explored challenges and the potential of AI tools. Data was analysed using Braun and Clarke’s thematic analysis, resulting in five central themes.

Persona Development

Based on interview insights, two personas—Alex (student) and Sarah (staff)—were created to guide the next stages. Their user stories helped shape feature ideation and AI use case discussions.

Phase 2: Co-Design Workshop

The workshop lasted 90 minutes and included six students. It featured two activities, the first being Empathizing with Personas, where participants explored persona pain points, identified opportunities, and proposed features for an AI tool designed to meet their needs.

Results

Activity 1 in the co-design workshop validated Phase 1 findings from the interviews, reinforcing the 5 central themes. These insights were synthesized into a chart, providing empirical data for the research.

User Journey Map

Although not part of the final report due to time constraints, I created a user journey map, flow, and storyboard to better illustrate Alex’s experience with the AI chatbot. These visual aids clarify key touchpoints, pain points, and interaction steps, enhancing understanding of the user’s goals and actions.

Persona: Alex
Goal: To learn how to register for the Language Resource Centre and find part-time work opportunities.

User Flow

Storyboard

Co-Designing the AI Chatbot Prototype

In the next part of the co-design workshop, participants were given a Design Brief and guided to sketch a preliminary concept for an AI chatbot. Reference examples were shared to support and inspire their ideas.

Results

Next, we created a series of AI chatbot prototype sketches while collaboratively identifying key features - such as accessibility options, language translation tools, and the ability to save and email conversations. These insights were compiled into a comprehensive Design Guideline document.

Phase 3: Prototype Design

Using the sketches and the list of features derived from the co-design workshop, I constructed a mockup of the envisioned AI chatbot tool, using the Figma software.

To ensure contextual alignment, I incorporated a screenshot of Newcastle University's landing page into the mockup.

I also designed an expanded version of the AI chatbot tool that would take up the full screen, tailored for current users within the university system, such as existing students and staff members.

Phase 4: Expert Evaluation

To validate the design, I applied Jakob Nielsen's 10 Usability Heuristics and conducted an evaluation with an industry expert—a seasoned software engineer based in Southeast Asia, well-versed in both heuristics and UX design.

The assessment took place over a Zoom call, where I provided access to my Figma prototype for review. Additionally, I shared a user-friendly, fillable form based on the Heuristics Guidelines template to streamline feedback collection.

Results

The Heuristic Evaluation revealed valuable usability insights, highlighting key areas for improvement to enhance system usability and user experience.

Limitations

Due to time constraints and limited resources, developing a fully functional chatbot prototype wasn’t feasible. This meant that some usability features couldn’t be fully demonstrated.

However, I chose to conduct an Expert Evaluation to gather valuable insights for future design iterations and gain hands-on experience applying Nielsen’s 10 Usability Heuristics.

Previously, my evaluations focused on Cooperative Evaluation reports using the think-aloud protocol. This presented a great opportunity to challenge myself with a new approach.

Conclusion

Research Questions: Answered ✅

Drawing on the comprehensive data collected across four distinct research phases, this research has illuminated several key insights which answer the research questions and delivered an artefact in the form of a prototype of the conceptual AI chatbot tool in this context.

Furthermore, wider implications have been identified and listed below.

Next Steps

For future work, it is hoped that this continued exploration into the boundless potential of AI tools such as GPT will persist. This research project, at the very least, seeks to kindle and propel future initiatives within this domain.