Market research is always evolving. The challenge is finding new ways to analyze data, text, and information to generate actionable insights and outcomes. A new technique and term that has grown in popularity in the past 5 years is text analytics. What is text analytics? Text analytics is simply a way of analyzing text and generating insights from patterns, trends, and ways of speech.
Without text analytics, your open-ends might look something like this:
A simple application for text analytics is open-ended comments from a survey. Many surveys use an NPS or likelihood to recommend question in the script with an immediate follow-up of "why did you rate it a 7?" Reading through and coding 5,000 open-ended comments can be a very time consuming process for an analyst. Text analytics can use a number of different analytic techniques including the following:
- Categorization (similar to coding) where you group responses and text into specific topics or labels
- Sentiment where you group responses into attitudes based on the text (positive, neutral, negative)
- Narrative top-lines where you summarize the information in the text to create a one or two paragraph takeaway
- Driver analysis where you determine what the key drivers are which are guiding text responses
Another common example of where text analytics is applied is through social media. Depending on your company or brand there may be a ton of conversation online. Trying to keep track and code all of this information across the globe is virtually impossible. By using software tools that track and manage text analytics it allows the process to be streamlined and automated. These types of programs do all of the leg work for you and deliver categorization, sentiment, narrative, and driver analysis right to your doorstep.