How we surface customer complaints, wants and needs through text analysis?

Customer Problem

Customer feedback is obtained from various sources including customer surveys, customer reviews, Twitter and customer support conversations. All this data put together is actually a gold mine for understanding what customers REALLY want. It can be a powerful tool for discovering new opportunities for innovation and can help pin point nagging problems in your products or services.

Let’s take a healthcare example. If a hundred patients at a hospital complained about parking being limited at the hospital facility, then a corrective action by the administration could be to expand the parking structure to address this pain point. Similarly, if several hundred patients complained about hospital staff being rude, then the hospital could decide to send their staff for training on how to better accommodate patients and their needs and dig further into the reasons for the rude behaviors. Are they being overworked? Or do they need to change their hiring approach?

Unfortunately, manually discovering such patterns, is not easy. You will have to read feedback from hundreds of users and this can become an error prone, mine numbing process. While out-of-the-box text analysis tools may seem like an option, often times our customers have found them to be too generic and lack the level of customization and detail that they want. Not to mention, you will also have to hire a data scientist or someone who is data savvy to help preprocess, tweak and interpret the results.


Customized Insights for Every Type of Feedback Data

Our approach is quite different in that we treat every feedback text analysis problem as being unique, because they are. Responses from open-ended survey questions would arguably be different from user reviews on the Web. User reviews are starkly different from Tweets. On top of that, comments from a product domain would be quite different from comments in the healthcare domain (think vocabulary, facets of interest, types of complaints).

Our process to feedback text analysis starts by understanding your requirements and getting a handle on your data, to understand:

  • The type of noise there is in your data
  • How short or verbose the text to be analyzed is
  • The types of preprocessing or normalization that your data may require
  • A rough set of themes that may be present in your data
  • Types of analysis you would need in order to answer your business questions

Once we have a good understanding of your needs and the unique properties of your dataset, we use the appropriate Natural Language Processing, Machine Learning and Sentiment Analysis techniques to generate meaningful insights. This can be a combination of our in-house tools customized to work on your data to additional models built specifically to extract the type of desired insights. We then interpret all the results and compile a highly actionable summary so that you can immediately make data-driven decisions.


Benefits to Customers

From this service, our clients have been able to:

  • Detect organizational and product problems and come up with a plan of action before problems blew out of proportion
  • Find areas where they could introduce new features and services based on what customers were saying
  • Understand areas they have been excelling in and incorporate more of that in other parts of their business.


Custom Text Analysis in Action

Here are some examples of insights from our work.


Need help analyzing survey comments, support conversations, user reviews or tweets? We have a 2-3 week turnaround time. Get in touch for a free consult!