Rosenverse

This video is only accessible to Gold members. Log in or register for a free Gold Trial Account to watch.

Log in Register

Most conference talks are accessible to Gold members, while community videos are generally available to all logged-in members.

[Case Study] Qualitative synthesis with ChatGPT: Better or worse than human intelligence?
Gold
Tuesday, June 4, 2024 • Designing with AI 2024
Share the love for this talk
[Case Study] Qualitative synthesis with ChatGPT: Better or worse than human intelligence?
Speakers: Weidan Li
Link:

Summary

Following the emergence of Generative AI as a potential revolution in the UX field, a great deal of AI-driven tools arose to enhance the efficiency of UX research, including data analysis. Qualitative data analysis is a process that conventionally relies on human intelligence to discern patterns, establish connections, and derive actionable insights and frameworks. Many studies have involved comparing the quality of qualitative analyses generated by humans with those produced by AI language models like ChatGPT (Hamilton et al., 2023). Despite the undeniable appeal of automation and speed, there is ongoing debate about AI’s ability to replace human intelligence in qualitative analysis, which may be unlikely at this moment. Then the question is: To what extent can AI contribute to qualitative data analysis? In this case study, I delved into the thematic analysis and post-analysis stage, i.e. synthesizing insights into a framework. Framework, in this context, refers to a conceptual structure that illustrates the components of a human experience and how the components interconnect and operate within the structure. It is a concise model that encapsulates the entirety of research insights. The topic of my case study is "trust relationships between job seekers and hirers in the marketplace,, aligning with the business focus of my company. From my secondary research, I found that, ChatGPT needed multiple rounds of training using diverse prompts to conduct precise and comprehensive thematic analysis. ChatGPT can execute fine-quality thematic analysis under the help of right prompts, yet it falls short in replacing human intelligence for synthesizing insights and crafting frameworks for engaging narratives. Its limitation lies in lacking the depth of contextual understanding within a company, such as understanding what’s missing from the company’s mainstream discourse to create a human-centered story based on data analysis. To craft a framework that conveys good storytelling and organizational impact, it requires the researcher's introspection into knowledge gaps in the specific organizational context. Thus, the best practice is to combine human interpretation and AI production. In my talk, I will demonstrate several principles to guide this practice. Takeaways We’ll cover principles of how to employ ChatGPT in qualitative analysis, specifically focusing on its application in synthesizing and crafting frameworks that convey compelling and insightful narratives: Effectiveness of ChatGPT in thematic analysis: Learn about my process of training ChatGPT to conduct precise thematic analysis. You’ll gain insights into the capabilities and limitations of ChatGPT in providing accurate and comprehensive analysis for framework construction Value of human potential: We’ll address the value of human self-reflection and the ability of interpreting organizational context for crafting engaging frameworks Comparison between human and ChatGPT: By comparing the human-driven outcomes against ChatGPT for qualitative analysis, you’ll see how effective the synthesized frameworks are generated by the researcher and ChatGPT separately. Collaboration between human and ChatGPT: You’ll also learn when and how to incorporate human interpretation with ChatGPT to achieve the best practice in qualitative analysis and synthesis

Key Insights

  • ChatGPT provides thorough and comprehensive qualitative summaries, often catching details humans might miss due to fatigue.

  • AI struggles to create appropriate hierarchical organizing themes, often equating basic and organizing theme levels.

  • ChatGPT’s thematic outputs lack experiential connection and the subjective 'eye' humans have during data synthesis.

  • Frameworks generated by ChatGPT tend to be siloed, lacking interconnectivity and coherent storytelling.

  • ChatGPT fails to generate a single, cohesive analogy for complex conceptual frameworks, often producing disjointed metaphors.

  • Human curiosity and first-person immersion in data drive better abstraction and insight creation than AI currently can.

  • Manual qualitative synthesis resembles a cinematic experience, while AI synthesis is like watching a recap video.

  • Using AI as an assistive tool to validate and triangulate human findings leads to better insights than fully relying on AI.

  • Prompt customizations and role-playing with ChatGPT have limited ability to improve the quality of generated frameworks.

  • ChatGPT excels at quantitative content analysis tasks, such as counting word frequencies in qualitative data.

Notable Quotes

"How good is ChatGPT at synthesizing qualitative data?"

"The problem with ChatGPT’s organizing themes is many are at the same detail level as basic themes."

"AI doesn’t have an eye engaged in the sense-making experience, only rapid summaries."

"Qualitative synthesis is not supposed to be as straightforward as how AI does it."

"Manual qualitative synthesis is like watching a movie in a cinema, AI synthesis is like watching a recap video on YouTube."

"Curiosity is the main drive in fulfilling cognitive needs that lead to new knowledge and understanding."

"ChatGPT significantly outperforms me in thoroughness when analyzing large qualitative data sets."

"We shouldn’t take ChatGPT’s answers as conclusions but as stimuli for new perspectives."

"Using AI to quickly summarize is helpful, but we should slow down when human intelligence is needed for sensemaking."

"Prompt tweaks and role changes didn’t fundamentally improve framework quality because the problem lies in how insights are generated."

Ask the Rosenbot
Chris Geison
What is Research Strategy?: A Panel of Research Leaders Discuss this Emergent Question (Videoconference)
2021 • Advancing Research Community
Dan Donald
Design Systems as a Vehicle for Systemic Change (Videoconference)
2023 • DesignOps Community
Jen Cardello
Learning Velocity—The Insights Speedometer (Videoconference)
2021 • Advancing Research Community
Billy Carlson
Tips to Utilize Wireframes to Tell an Effective Product Story
2023 • Enterprise UX 2023
Gold
Amy Marquez
INVEST: Discussion
2018 • Enterprise Experience 2018
Gold
Gonzalo Goyanes
Design ROI: Cover a Little, Get a Lot
2022 • DesignOps Summit 2022
Gold
Brendan Jarvis
Framing Tomorrow by Questioning Today
2022 • Design at Scale 2022
Gold
Maria Skaaden
Panel Discussion: Methodologies and Work Environments
2018 • DesignOps Summit 2018
Gold
Nick Cochran
Growing in Enterprise Design through Making Connections (Videoconference)
2019 • Enterprise Community
Yunyan Li
UX Best Practices
2021 • Design at Scale 2021
Gold
Tricia Wang
Spatial Collapse: Designing for Emergent Culture
2024 • Enterprise Experience 2020
Gold
Saara Kamppari-Miller
Inclusive Design is DesignOps
2021 • DesignOps Summit 2021
Gold
Christopher Noessel
AI of the now: Designing for Agents
2024 • Rosenfeld Community
Molly Fargotstein
Multipurpose Communication & UX Research Marketing (Videoconference)
2019 • DesignOps Community
Séamus Byrne
Aligning Teams with Choreography
2024 • Enterprise Experience 2020
Gold
Sheryl Cababa
Expanding your Design Lens with Systems Thinking
2023 • Advancing Research 2023
Gold

More Videos

Zariah Cameron

"Share everything, own nothing but credit everyone."

Zariah Cameron

ReDesigning Wellbeing for Equitable Care in the Workplace

September 23, 2024

John Cutler

"The top priority is often the lack of a priority, resulting in teams spending 50% of their time jumping between priorities."

John Cutler Harry Max

Prioritization for designers and product managers (1st of 3 seminars) (Videoconference)

June 13, 2024

Nick Cochran

"As leaders, don’t make it about you—put the spotlight on the people doing great work."

Nick Cochran

Growing in Enterprise Design through Making Connections

June 3, 2019

Deanna Smith

"Documentation helps explain the rationale and revisit decisions in the future, preventing repeated mistakes."

Deanna Smith

Leading Change with Confidence: Strategies for Optimizing Your Process

September 23, 2024

Magdalena Zadara

"Quick wins help build trust and get stakeholders willing to work with you."

Magdalena Zadara

Zero Hour: How to Get Far Quickly When Starting Your Digital Service Unit Late

November 16, 2022

Nova Wehman-Brown

"The designers were taking a part of their job away, and it was something the developers really loved."

Nova Wehman-Brown

We've Never Done This Before

June 4, 2019

Liwei Dai

"To be truly impactful, we need to actively participate in product design sprints, ideation, and key strategy meetings."

Liwei Dai

The Heart and Brain of the AI Research

March 31, 2020

Gordon Ross

"The arrival of workers during COVID lockdown meant coordinating across government ministries, airport authority, federal border services and public health – this was a design problem."

Gordon Ross

12 Months of COVID-19 Design and Digital Response with the British Columbia Government

December 8, 2021

Tutti Taygerly

"Listening to the 10% truth means acknowledging a bit of what they say even if you’re irritated."

Tutti Taygerly

Make Space to Lead

June 12, 2021