David McDonald's Research Group Archives

The following research group descriptions are archived because they are no longer offered, the faculty member is on sabbatical, or the group is taking a break. Please contact the faculty member or an advisor to learn more about these groups.

Exploring LLMs for UX Design Critique
Can GPT detect harassment, bullying and hate speech?
Designing with Large Language Models for Debugging Assistance
Analyzing How UX Practitioners Communicate AI Enabled Apps
Designing TikTok Videos to Explain Wikipedia
Understanding the collaborative behaviors of Spanish Wikipedia editors
UX Skills + ________ = Leadership
A Human-Centered Design for Access to Justice
Pathways: Mapping HCDE career experiences
Do conflicts make the Spanish editions of Wikipedia better?
Do conflicts make the French editions of Wikipedia better?
Do conflicts make the English Wikipedia better?
Do conflicts make the French, Spanish and English editions of Wikipedia better?
Developing UX maturity in the corporate world
Do conflicts make Wikipedia better?
"That's not what I meant!" A Directed Research Group on Voice User Interactions (VUI)

Spring 2024

Exploring LLMs for UX Design Critique

Your faculty hosts:

Dr. Tyler Fox
Dr. David W. McDonald

Can an LLM generate a design critique? Well … sure it can. But is it any good? How would you know?

User experience professionals will soon encounter all types of tools driven by LLMs, GPT, or AI that will claim to make their jobs easier, provide feedback, and assess usability of their designs. Having a clear understanding of what these tools can or cannot provide will be important to being an effective professional in the new world of UX.

This DRG will explore how GPT and LLMs can be used to provide important design feedback on early stage design artifacts. Participants in this DRG will work with their own early stage designs - perhaps something they already have designed. Those designs will then be used to examine the quality and effectiveness of different types of critique generated by LLMs. Students will qualitatively evaluate the LLM generated critique to understand the different qualities of LLM feedback. During the quarter, students will work to engineer a ChatGPT prompt that will provide a selected form of critique.

Winter 2024

Can GPT detect harassment, bullying and hate speech?

Meena Muralikumar (HCDE PhD candidate) & David Mcdonald (HCDE Professor)

Supportive, informative and civil interactions are often important to the growth and long-term viability of any online community. Unfortunately, there will be times where some individuals will harass, bully or target others. In those situations, moderating the community becomes an important task.

Content moderation is a moving target. Adapting to this challenge requires monitoring and updating an understanding of hate speech, toxicity, and harassment. Re-training a dedicated and specific machine learning model requires additional labor, money, and time. Using a Generative Pre-trained Transformer (GPT) Large Language Model (LLM) shows promise in adapting to this challenge because of its natural language generation capabilities.

How might we leverage LLM capabilities to detect toxic/hate speech? Could one customize LLMs using prompt engineering and few-shot training to fulfill specific moderation policies or to conform to human judgements? How would it compare to human judgements of toxic/hate speech? We will explore such questions in this DRG.

In this DRG, we will be working with Open AI’s GPT-4. We will be exploring both the moderation endpoint and how to customize GPT-4 for content moderation. The main objective of this DRG is to compare our results with human judgements and/or other popular toxicity detecting classifiers such as Perspective, primarily using quantitative analysis methods.

What students can learn from this DRG:

Programming in Python, using Jupyter Lab Notebooks
Introductory methods for quantitative data analysis
Prompt engineering techniques for ChatGPT

Skills that would allow you to be successful in this DRG include :

Prior coursework programming with Python
A statistical methods course

Winter 2023

Designing with Large Language Models for Debugging Assistance

Instructors:
Dr. Colin Clement (Microsoft)
Dr. David W. McDonald

Being good at programming is partly a function of what you are taught in a course and partly the experiences you gain. Debugging a program when something goes wrong is often based on hard won experiences.

What if we could make some aspects of debugging easier?

This DRG will consider how to improve the debugging experiences of novice programmers using large language models (LLMs)---such as OpenAI's Codex---which can answer questions and offer edit suggestions leveraging both natural language and source code.

Software flaws or errors, sometimes generate 'exceptions' which often contain code context and dubiously helpful error messages. This DRG will use the knowledge retrieval and synthesis behaviors of LLMs to offer suggestions to overcome such errors quickly, inside the development environment.

In the DRG students will develop interactive prototypes for an IDE to capture exceptions, interact with an LLM and display possible solutions. These interactive prototypes will explore the possible user experiences that will help novice programmers overcome challenges and learn to unblock themselves.

Students who are the best fit for this DRG will minimally:

Have had 2+ programming courses
Have experience with prototyping techniques
Have used Python

Autumn 2022

Analyzing How UX Practitioners Communicate AI Enabled Apps

Help us analyze design pitches for proof of concept AI-enabled apps! We’ve collected design pitches (e.g. slide decks, documents) created by UX professionals who we challenged to prototype and pitch a proof-of-concept app that uses AI. This DRG will be focused on analyzing those artifacts to better understand how practitioners communicate to stakeholders the promises and challenges of AI in the context of the UX design process. Through our analysis, we hope to identify recommendations to better support UX practitioners when they communicate designs for AI-enabled apps. The end goal of this DRG is to submit a paper to the ACM Designing Interactive Systems (DIS) conference in early 2023.

In this DRG, you will learn how to:

Systematically and qualitatively analyze visual artifacts created by UX practitioners to communicate an AI-enabled app
Identify trends and insights from the analysis
Turn trends and insights into concrete guidelines for practitioners as well as an academic paper

The benefits for you are:

Getting first-hand exposure to working at the intersection of AI and UX
Learning how UX practitioners communicate technical concepts so you can incorporate them into your own work
Helping to create guidelines or recommendations that make direct contributions to HCI/UX industry and academic communities
Obtaining DRG credits for fall quarter

Spring 2022

Designing TikTok Videos to Explain Wikipedia

Led by: Julie Vera, PhD Student, HCDE
With guidance from faculty advisor Professor David McDonald and Professor Mark Zachry

We are looking for:

Up to 40 undergraduate or masters students 
Folks with experience or a strong interest in TikTok, video production, or visual storytelling 
Nice to have: 
- Interest in Wikipedia or other collaborative knowledge platforms 
- Interest in science communication or communication for public audiences 
- Interest in the design of learning or how-to experiences 
You do not have to be an expert on Wikipedia to participate!

About the DRG:

In this DRG, we will be thinking of new ways to introduce students to Wikipedia as a concept and platform. We will be designing TikTok videos that explain some important features and concepts of Wikipedia so that they feel equipped to contribute. We will follow a flexible design process to create short-form videos that are informative as well as fun and engaging. Participants in the DRG can expect to be lightly onboarded onto Wikipedia.

Students participating in the DRG will:

Conceptualize ways to introduce high-school and college-aged students to Wikipedia via TikTok 
Get (lightly) onboarded onto Wikipedia 
Think about what concepts are important to people who are just joining the platform 
Use a “how might we” approach to design video material that addresses important Wikipedia concepts 
Storyboard potential video content and collaborate with other students on audio and visual components 
Prototype TikTok videos for public consumption 
Respond to weekly reflection prompts about Wikipedia, content ideas, and design process

Expectations:

Attend weekly meetings (in-person; time 4:30 - 5:30pm on Mondays) 
Work in the DRG for 2 CR (6 total hours a week, including “class” time)  
Later in the quarter, we may choose to be remote and asynchronous due to the nature of the work

Please contact Julie (jvera@uw.edu) if you have any questions.

Winter 2020

Understanding the collaborative behaviors of Spanish Wikipedia editors

Co-directed by PhD student Taryn Bipat, and Professors David McDonald and Mark Zachry

While collaboration in the English Wikipedia has been researched extensively, these other language editions remain understudied. To further understand this challenge, we will explore the perspectives and experiences of the Spanish Wikipedia editors.

We are looking for fluent Spanish speakers for the Winter Quarter to help with conducting interviews with editors from the Spanish Wikipedia. We are interested in understanding the editing experiences of these editors and the interactions they have with other Wikipedia editors.

Activities of this research group will include working with the research team to recruit participants, conduct interviews, analyzing data and potentially write a conference paper to present the results to the broader community.

This DRG will require you to interview editors in Spanish. We are looking for students who are fluent in speaking and reading Spanish. Furthermore, we are looking for students, who have experience with or a willingness to learn (1) qualitative coding and (2) user behavior on online collaborative systems. Students interested should also be available for a 2-hour class each week and about 4-5 hours of work outside of these meetings.

If you are interested in participating, please contact: Taryn Bipat <tbipat@uw.edu>), HCDE PhD student.

Winter-Spring 2020

UX Skills + ________ = Leadership

Faculty Leaders:

Mike Berg, UX Researcher
David McDonald, HCDE Faculty

Student Coordinators:

Flower (Zhuofan) Hua, UW Student
Britnie Chin, UW Student

The path to UX Leadership is a mysterious one. There are various resources focused on the characterics of being a leader in the UX field, but there isn’t anything showing the path to leadership and how to get there in the UX community. This DRG will build off of the Pathways: Mapping HCDE career experiences lead by Mike Berg, Paula Chuchro, and David McDonald. During this two quarter DRG we will analyze secondary research, conduct interviews, analyze those interviews for success factors, to understand the meaning of Leadership in UX, and design a UX Leadership Playbook. DRG participants will need to participate in BOTH Winter 2020 and Spring 2020

Students who want to join the DRG should bring the following skills:

Experience conducting literature reviews (secondary research)
Experience conducting semi-structured interviews
Interest in creating information visualization in the form of a playbook

Logistics

We are looking for 12-15 students available for two academic quarters, who are available to meet Monday and Wednesday from 5 PM to 6 PM for Winter and Spring Quarters. This DRG is 2 credits per quarter and is open to both Undergraduate and Graduate students.

Brief Schedule

2020 Winter Quarter:

The team will explore the meaning of Leadership in UX from secondary research methods (collecting and reading existing literature). There will be weekly hands-on activities to understand research question, develop a study plan, and conduct mock interviews with feedback from professionals in the industry.

2020 Spring Quarter:

Based on the work from winter quarter, students will follow their study plan to conduct semi-structured interviews with industry leaders. Students will then begin to design a playbook composed of a small set of cases presented through timelines, key choices, types of experiences, that provided important leadership growth and development.

Winter 2020

A Human-Centered Design for Access to Justice

Co-led by: Jane K. Winn (UW Law), Ellen Reed (HCDE), David W. McDonald (HCDE)

This DRG will conduct a human-centered evaluation of the legal technology software A2J Author, develop and perform a usability study, and provide the results of the study directly to the developers of A2J Author. A2J Author is a free platform for legal aid organizations that supports the creation of technological tools that help people with legal problems who cannot afford an attorney. Participants will have the opportunity to create work that can be showcased in their portfolio, utilize a variety of qualitative and quantitative research methods, provide study findings directly to a "client", and contribute to the promotion and development of technology designed to increase access to justice.

Pathways: Mapping HCDE career experiences

Summer 2019

Directed by Mike Berg and Paula Chuchro

The HCDE Alumni Leadership Board wants to partner with HCDE students to explore the journey that HCDE grads take in their careers. We want to identify the diverse range of careers that HCDE students pursue after graduation as well as key transitional moments in their lifelong careers. We’ll analyze survey data, conduct primary research, compare the HCDE experience with other programs, and develop user personas and a journey map. Research efforts will support the Alumni Leadership Board in planning events and continuing education efforts for HCDE students and Alumni.

Members of the directed research group will work closely with members Alumni Leadership Board, and will have a chance to connect with alums working in a diverse range of companies, roles, and levels. The board will help students make connections with alums and can offer some access to workplace research labs.

Students interested in joining the research group should have an interest in conducting user research with alums working in a wide range of professional roles, as well as working on conceptual models to summarize user research findings. Desired skills include:

Experience with executing and presenting secondary research
User profiling and persona creation
Experience conducting semi-structured interviews
Interest in creating information visualizations to summarize research findings

The group will hold weekly meetings on Tuesdays from 4:00 – 5:00 PM, alternating between Seig Hall, Room 129 and a meeting space at the Amazon or Hulu offices downtown Seattle.

HCDE undergraduate or graduate majors will participate in this research group by enrolling for 2–4 credits (graded cr/no cr) in HCDE 596 (for graduate students) or HCDE 496 (for undergraduate students). Students are expected to spend, on average, three hours of effort per credit per week (time spent includes the weekly meeting). Interested students should contact Mike Berg.

Do conflicts make the Spanish editions of Wikipedia better?

Spring 2019

Co-directed by PhD student Taryn Bipat, and Professors David McDonald and Mark Zachry

How many times has Wikipedia articles saved you from failing a homework assignment? Those articles would not have been of so much help if it were not for the contributors. These contributors do not always agree with each other. In this DRG, we will address how the conflict arises in the Wikipedia community.

To further understand this challenge, we will explore how editors behave across the various language editions of Wikipedia. While collaboration in the English Wikipedia has been researched extensively, these other language editions remain understudied. The goal of this project is to understand editor behavior in the English and Spanish language edition of Wikipedia.

We are looking for students during Winter quarter to help with a study understanding how conflict occurs between Wikipedia’s editors in the English, French, and Spanish Wikipedias. As part of this research, we will be exploring the literature around editor conflict and multilingual Wikipedia. We will be qualitatively coding editor comments in each language to understand how conflict arises across different language platforms.

Do conflicts make the French editions of Wikipedia better?

Spring 2019

Co-directed by PhD student Taryn Bipat, and Professors David McDonald and Mark Zachry

Do conflicts make the English Wikipedia better?

Spring 2019

Co-directed by PhD student Taryn Bipat, and Professors David McDonald and Mark Zachry

We are looking for students during Winter quarter to help with a study understanding how conflict occurs between Wikipedia’s editors in the English Wikipedia. As part of this research, we will be exploring the literature around editor conflict and multilingual Wikipedia. We will be qualitatively coding editor comments to understand how conflict arises across different language platforms.

We are looking for students, who have experience with or a willingness to learn (1) qualitative coding and (2) user behavior on online collaborative systems.

Do conflicts make the French, Spanish and English editions of Wikipedia better?

Winter 2019

Co-directed by PhD student Taryn Bipat, and Professors David McDonald and Mark Zachry

We are looking for students, who have experience with or a willingness to learn (1) qualitative coding and (2) user behavior on online collaborative systems (3) Reading comprehension in either French or Spanish is necessary. This DRG will be organized into three separate committees for each language.

Being a part of this DRG would require attending a Saturday Wikipedia workshop on January 12 from 9 a.m.-2 p.m. During the quarter, the DRG will be held every Wednesday from 4-5 p.m.

This is a 2-credit research group offered to undergraduate (HCDE 496) and graduate (HCDE 596) students. If you are interested in participating, please fill out this google form.

Developing UX maturity in the corporate world

Autumn 2018 - Winter 2019

This DRG is for students who are interested in how academic research and real-world business do (and don’t) mix.

UX consulting is a booming business. However, the lack of systematic research on how technology companies learn to adopt UX practices can leave corporate stakeholders skeptical of whether investing in UX is worth it. This DRG provides students with a unique opportunity to work directly with a real-world software company, while also helping to build a body of scientific research on how UX maturity develops in corporate settings.

As a member of the HCDE Corporate Affiliates Program, nFocus Solutions has offered to serve as a research partner for this DRG, focused on understanding how a medium-sized technology company with a legacy enterprise system works to advance itself through the stages of UX maturity. nFocus Solutions is a SaaS (software-as-a-service) provider of datamanagement, outcome measurement and performance management software to the public sector. They serve a wide range of clients across the public sector, ranging from single nonprofits serving 30 children a day, to entire communities working to improve high school graduation rates, to first responders performing search and rescue missions, to the United States Army.

The quarter will culminate in a presentation to nFocus Solutions.

Activities

This DRG will meet from 4 -5:30 p.m. on Thursdays in Fall 2018 (2 credits) and will be led by David McDonald (HCDE), David Ribes (HCDE), and Emily S Lin (nFocus Solutions).

Students will begin the quarter getting oriented to relevant research literature, as well learning about nFocus Solutions and their clients. Over the course of the quarter, students will identify a research contribution they’d like to make (e.g., developing a survey instrument, testing a feedback mechanism), then do field work with nFocus employees to refine their methodology. The final deliverable will be a presentation to nFocus stakeholders.

Recommended Background

This DRG is most suitable for students of all levels (BA, MS, PhD) with an interest in both the research and business sides of user-centered design. Students with a background in organizational studies, social psychology, psychometrics, and/or ethnography are encouraged to apply. We also welcome students experienced with database technologies and/or social service or public sector end-users.

How to Apply

Please submit your current resume/CV and a short statement (2 paragraphs max) explaining why you are interested in this DRG to:

Emily S Lin, elin@nfocus.com, and David McDonald, dwmc@uw.edu.

Do conflicts make Wikipedia better?

Spring 2018

To further understand this challenge, we will explore how editors behave across the various language editions of Wikipedia. The English language Wikipedia is notable for its enormous database but there are also 288 other active language editions. While collaboration in the English Wikipedia has been researched extensively, these other language editions remain understudied. The goal of this project is to understand editor behavior in the English, French and Spanish language edition of Wikipedia.

We are looking for up to 8 students during Spring quarter to help with a study understanding how conflict occurs across Wikipedias. As part of this research, we will be exploring the literature around editor conflict and multilingual Wikipedia. Additionally, we will replicate prior methods used to understand this platform to check whether prior assumptions still hold true across different language samples and in present day Wikipedia.

We are looking for students, who have experience with or a willingness to learn (1) qualitative coding and (2)user behavior on online collaborative systems. It is not necessary but French and Spanish language skills will be helpful.

This is a 2-credit research group offered to undergraduate (HCDE 496) and graduate (HCDE 596) students. Students will meet for 1 hour every week (Tuesday 4-5pm) and should commit around 4 hours outside of class time.

"That's not what I meant!" A Directed Research Group on Voice User Interactions (VUI)

Summer 2016

During the last few years products have entered the market that feature voice based interaction. Voice based agents like Siri, Cortana, and Alexa promise a seamless style of interaction based on voice command or, very nearly, conversational interaction to understand the goals of the user and act on the user's behalf.

This DRG will focus on one specific device, the Amazon Echo, to explore the limits of voice interaction and design new possible interactions. The DRG will explore how to use the Alexa Skills Kit (ASK) API to expand the capabilities of Alexa to prototype new visions of voice user interactions.

"That's not what I meant!" A Directed Research Group on Voice User Interactions (VUI)