HumanListening has announced two major updates to its platform: time series analysis for qual AI and a new way to measure the effectiveness of your qualitative outputs. Both updates are available now to HumanListening customers.
Tracking studies are built to show movement, but too often they fall short of explaining what is driving that movement. Time series analysis for Qual AI changes that. Customers can now track how topic mentions and sentiment shift across the life of a study, giving research and insights teams a view of how people's thinking evolves. Instead of relying on flat lines or static readouts, customers can see the qualitative drivers behind change, with Gen AI summaries and statistical testing surfacing the most important callouts for decision-making.
The second update addresses a different problem: knowing whether an open-ended response is actually worth building a decision on. The platform now includes two new scores, Text Quality Score and Human Insights Factor, that measure the quality of the feedback teams are receiving. Text Quality Score evaluates reading ease, conversation length, and detection of AI or gibberish. Human Insights Factor evaluates the number of topics, network edges and density within a response. Together, the two scores give teams a consistent way to judge whether their qualitative data is rich enough to act on.
"These updates are about giving research teams a real answer to what's really driving the changes in my study and how robust is the qualitative data to support my decisions?" said Chris Barry, Managing Partner at HumanListening.