How to Use Human-Led AI to Code your Verbatim Data
Open-ended survey questions have always been a double-edged sword.
We know they yield lots of useful details about “why,” and we’d like to use them more in our research, but they’re such a pain to deal with, aren’t they?
The recent explosion of generative AI technologies has offered a glimmer of hope to those facing this pain. Indeed, many now believe, with the application of generative AI, analyzing survey verbatim data is now a solved problem – or will be within the next few years.
At codeit, we have been working on the application of AI to this problem for over seven years. In this presentation, we’ll discuss what we’ve learned along the way and the results of our recent experiments with generative AI. Is the hype true? Is it time to fire all of your coders and just let ChatGPT do all your coding?
In this presentation you will learn about:
· How state-of-the-art AI techniques can be applied to verbatim coding
· The strengths and limitations of these techniques
· Why you should be thinking in terms of human-led AI
· Our predictions for where the technology is headed in the future
Sometime after the Y2K bug he was drawn into the world of software development and has been writing software for the market research industry ever since.
In 2016, he saw that AI presented a huge opportunity to the research industry and co-founded codeit as a vehicle for bringing these two worlds together.
codeit uses a blend of advanced artificial intelligence, machine learning, text analytics and human supervision to code open-ended survey responses.
