Everyone thinks they want video collection in their research projects. Yet, simply watching video responses often results in hearing things you’ve already heard 100 times about your brand / category: Yes, consumers want their experience to be convenient… Yes, they want superior product performance… No, they don’t want to have to wait…
At face value, these videos are disappointing because there’s an assumption that ‘the truth’ will be revealed. However, they often only serve to highlight information that your team already knows.
So – how can a team interpret those voice-of-consumer nuggets so that they bring greater meaning and insight?
Allow me to tell you a bit about our video analysis approach at Alpha-Diver….
We know that people are not good at explaining how they feel. So, along with my analytic partner-in-crime, Bill Godsil, PhD, we employ a natural language processing (NLP) technique to read between the lines..
Why should a team use NLP? How is it different?
NLP provides ways to detect signals within open-ended text-based responses (and transcribed video responses), such as sentiment (negative and positive emotional valence) that would otherwise be quite laborious to measure. For example, it can uncover whether Segment A talks more positively about Product X, compared to Segment B.
The NLP process involves processing data into the software, extracting text variables, and then applying a set of algorithms. From there, the text is used in sentiment analysis and other text-mining procedures, both at the level of the words used by a group, or at the level of individual sentences/phrases by participant.
TRANSLATION: By implementing analysis beyond simply watching / coding video, this process gives our team the tools to understand consumers far beyond what they say, or what they think they think.
How does Alpha-Diver’s database come into play? What does it allow us to uniquely understand?
Through our database of past studies that contain thousands of neuropsych profiles, we have a rich resource on how different types of people tend to write/talk. From these data, we establish group norms for the expression of sentiment, and in doing so, we compare the open-ended data from new studies to the database.
These steps allow us to infer which subconscious drivers and barriers a person may be expressing based on what they say/write.
TRANSLATION: Our ever-expanding database informs our understanding of drivers and barriers that relate to, among others, attention style and information bias, decision making style, and ultimately HOW to reach these consumers in real life.
So, when you think you’re not hearing anything new, consider taking your data a step further. The ‘magic’ of neuroscience reveals deeper insights from NLP that consumers themselves don’t even recognize. In short, it elevates responses from ‘what they say’ to WHAT THEY MEAN.