Would having a system for classifying usability problems be helpful to UX researchers and designers? Would it reduce the evaluator effect? Categorization frameworks have been around for decades, but in our experience, they haven’t seen a lot of adoption by commercial development teams. There are probably a few reasons for this: they might not be
ChatGPT is probably not going to take your UX research job. However, another researcher who can use AI tools such as ChatGPT effectively might. In an earlier article, we explored using ChatGPT-4 to augment researchers’ abilities to sort open-ended comments. We found that the results were comparable to how humans performed, although they had some
Do researchers agree on what the problems are in an interface? And will researchers group the problems into the same categories? When coding open-ended comments in a survey, will different researchers classify the comments differently? These discovery and classification activities are quite common in UX research, but they are often conducted by a single person
ChatGPT. A sequence of letters that didn’t mean much to people a few months ago is now ubiquitous. It seems like every social media post mentions ChatGPT (especially the latest version, 4) and hypes it as a game changer. It’s been used to quickly summarize text, do homework, pass the bar exam, and code the game Duck Hunt
