Physical Address

304 North Cardinal St.
Dorchester Center, MA 02124

Advancing AI-Driven Qualitative Analysis in Asia: A Case Study


Advancing AI-Driven Qualitative Analysis in Asia: A Case Study

Per Fuel ASIA

  • AI
  • AI moderation
  • Qualitative research
  • Qualitative data analysis
  • Online qualitatively
  • Generative AI
  • Artificial intelligence

The potential of artificial intelligence in qualitative research is transformative, promising faster insights, scalability and innovative new approaches to data collection, analysis and reporting. As the pace of AI transformation accelerates, research platforms are making significant strides in improving language and analytics support for different regions. However, when it comes to application in Asian markets, the road to realizing the potential of artificial intelligence is complex.

On FUEL Asiawe recognized an industry-wide need for rigorous, experience-based validation of AI tools to assess their true potential for non-Western language and cultural contexts. This case study is part of that journey where we test AI-driven qualitative research methods using real-world data in the Thai language, measuring the strengths, limitations and overall effectiveness of each approach.

Democratizing research innovation: How AI is reshaping qualitative research

As a sister article to Democratizing research innovation: How AI is reshaping qualitative researchthis section explores how different research technologies perform when confronted with the nuances of Asian languages. It provides a practical, science-backed look at three main approaches: traditional human-only analysis, commercially available qualitative research platforms, and a DIY AI approach that uses generic AI tools not specifically designed for market research. Our goal is to shed light on how these methods stack up and highlight unique considerations and potential solutions for using AI tools to conduct qualitative research in Asia.

Stay tuned

Subscribe to receive Research Tool Radar and essential updates via email from Insight Platforms.


An overview of the experiment: Three approaches to qualitative analysis

This case study explores three approaches to qualitative analysis on a dataset of 10 online in-depth interviews conducted in Thailand. Each method offers different advantages and challenges, allowing us to test the limits of their regional adaptability and effectiveness.

  1. Analysis for humans only: As a baseline, we used the skills of an experienced qualitative researcher to manually interpret the data. This traditional approach remains the gold standard for nuanced insights, setting the bar for quality.
  2. Commercial technology platforms for qualitative research: These specialized platforms are specifically designed to handle qualitative data at scale. In this case study, we tested 3 platforms. They offer user-friendly interfaces and often claim to be compatible with different languages, enabling simplified analysis, rapid implementation and transparency in source findings. However, as we will discussthese platforms seem to show developmental lags in supporting some Asian languages.
  3. “DIY AI”: For our third approach, we adopted a more flexible DIY AI strategy, combining AWS for transcription, ChatGPT 4o for analysis and initial reporting, and Gamma.app to create a more visual PowerPoint report. Although neither tool was designed specifically for qualitative research, this setup allowed us to design an end-to-end solution for the entire analysis and reporting process.

Analysis for humans only

Our researcher watched the interviews live and took extensive notes, allowing the researcher to capture subtle cues and contextual nuances in real time. Using a mixture of thematic and narrative analysis, the researcher systematically identified recurring themes while also weaving in the narrative flow of each interview. This approach set the bar for quality, providing a rich, detailed understanding of the data and serving as a valuable benchmark for comparing AI-driven methods.


Commercial technology platforms for qualitative research

Commercial qualitative research platforms are designed specifically for simplified, high-quality analysis. These tools are already delivering on promises of simplicity and scalability, helping us generate insights faster than ever. While some challenges remain in supporting Asian languages, we view these platforms as critical and believe they will continue to improve as demand in the region grows.

  • User friendly design: These platforms are built for quick deployment and typically require little or no training. They are intuitive, built to guide users through analysis with minimal friction, making them an attractive choice for fast-moving projects.
  • Transparency and segment analysis: Unlike some DIY approaches, commercial platforms allow users to trace findings back to their sources, increasing transparency and giving users confidence in their analysis. They also streamline segment-specific analysis and guide the production of supporting media, such as video reels, that are often critical to stakeholder engagement.
  • Gaps in language development: However, when it comes to the Thai language, these platforms reveal a significant lag in development. Different platforms presented different problems; one platform could not recognize Thai in Zoom audio files, even though it claimed to support the language. Another platform required us to split the analysis into two parts (due to platform token limitations), which meant we had to create two reports and later manually combine them (using ChatGPT as a workaround).

Given the current pace of change, all AI tools are now ‘work in progress’ and current commercial offerings may work better in some contexts than others. This is sure to change quickly with ongoing development, fueled by increasing demand from our region. Once the language issues are resolved, it will offer an affordable and user-friendly option, especially for researchers with limited technical resources or time or willingness to experiment.


The ‘DIY AI’ approach: Flexibility, customization and cost

The flexibility of the DIY AI approach was clear from beginning. With the three main tools we used, we created workflows that were highly tailored to the needs of our project, including the desire to maintain a consistent brand identity and style. These workflows can be easily adapted to different projects or client needs. The customization potential here was unparalleled, allowing us to experiment with different approaches to qualitative analysis to quickly and iteratively create something we were proud to put our brand behind.

While this flexibility offers an advantage, it comes with an initial time investment. Unlike specialized platforms, setting up DIY AI requires initial adjustments to workflows and queries, along with trial and error to get the best results. However, this flexibility can be a huge advantage, allowing us to quickly tailor analysis and reporting to meet the unique needs of each project. Apart from the time cost, this approach is inexpensive – a subscription to Chat GPT and about $15 in transcription costs.

Our results show that, when designed well, DIY AI can match – and sometimes even outperform – commercial platforms. With carefully crafted instructions and outputs compliant with FUEL Asiastandards, we have maintained strong control over the quality of analysis and reporting. This adaptability is key to creating tailored, impactful and powerful insights.


Comparing Three Approaches: Key Findings for Asian Markets

When evaluating our findings across all three approaches, several key findings emerged, highlighting both challenges and opportunities in implementing AI-driven qualitative research for Asian markets.

  1. DIY AI as a solution to language and localization gaps: In our experience, DIY AI is emerging as a viable and powerful solution to overcome the current limitations in language support. This flexible, high-control approach allows researchers to achieve depth without the constraints of current platform limitations, proving that AI as a copilot can be transformative for qualitative research when precisely tailored. The potential for ‘better’ qualitative research using artificial intelligence as a co-pilot already exists.
  2. Addressing Development Gaps in Asia: The unique requirements of Asian markets require more attention from platform developers. While commercially available platforms offer off-the-shelf solutions, they seem to work better with some languages ​​than others, making the DIY approach an attractive alternative. For qualitative researchers working in Asian markets, DIY AI offers greater control over language handling and analysis and reporting approaches, enabling deeper insights without relying solely on tools that may not yet fully support non-Western languages.
  3. Localized pricing for market penetration: FUEL Asia believes that localized pricing, along with culturally responsive development, will be key to driving platform adoption in Asia, ultimately benefiting the global industry with more inclusive AI tools. The cost of creating human transcripts and analyzing people is relatively low in some of the countries we work in, and commercial tools should be priced accordingly.

The way forward: We call on the industry to bridge the gap

As our case study demonstrates, AI is a powerful enabler for qualitative research, with the potential to improve analysis speed, consistency and adaptability. However, from our initial small trial, it appears that much needs to be done to bridge the development gap in Asian markets, where language and budget issues present different challenges. To advance the conversation and explore new solutions, FUEL Asia teamed up with Insight platforms to co-host the upcoming Asia Digital Insights Summit in January, a landmark event for the research community in Asia, bringing together leaders in research and technology discuss the future of technology-driven insights in Asia.

The summit will feature a dynamic agenda, including keynote sessions, expert panels and live demonstrations of breakthrough research technologies – addressing both quantitative and qualitative use cases.


Conclusion: Collaboration for an AI-driven future in Asian research

This case study illustrates the development of artificial intelligence in qualitative research, where both customized DIY approaches and specialized platforms have a role to play. FUEL Asia remains committed to advancing this dialogue, and we invite you to join us at Asia Digital Insights Summit. Together, we can drive research innovation that strengthens the industry, creating solutions that meet the diverse and growing needs of Asian markets.

About FUEL Asia

FUEL Asia

FUEL Asia provides in-person and online qualitative research and cultural insights to identify growth opportunities for brands across Asia.

Author



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *