Feedback Ferret logo
Page Loading...Please Wait

Correct interpretation is key to text analytics

One of our clients recently told us

“The Feedback Ferret text analytics engine clearly delivers better results than any other tool we have ever used”.

Although we were chuffed to bits to hear this, it’s worth understanding why highly accurate text analytics results are so important in today’s world when there are plenty of text analytics providers out there to choose from.

Here’s a great analogy:

Once upon a time, there lived six blind men in a village. One day the villagers told them, “Hey, there is an elephant in the village today.” They – the six blind men – had no idea what an elephant was. … They decided, “Even though we would not be able to see it, let us go and feel it anyway.” All of them went where the elephant was. Every one of them touched the elephant.

“Hey, the elephant is a pillar,” said the first man who touched his leg.

“Oh no, it is like a rope,” said the second man who touched the tail.

“Oh no, it is like a thick branch of a tree!” said the third man who touched the trunk.

“It is like a big hand fan,” said the fourth man who touched the ear of the elephant.

“It is like a huge wall,” said the fifth man who touched the belly of the elephant.

“It is like a solid pipe”, said the sixth man who touched the trunk of the elephant.

As the story demonstrates, each individual can interpret a situation differently. We are in the business of text analytics so interpretation of the written word is our world. If we don’t interpret text correctly, it is worthless.

In side by side comparisons, the Feedback Ferret text analytics engine has proven to deliver results which are substantially better than Natural Language Processing engines, both in terms of topic identification and accuracy of sentiment scores.

This is critical, as you need to be able to rely on what the reporting tool is telling you so that you can make robust business decisions.

Feedback Ferret achieves over 93% accuracy rates for contextual analysis, ensuring that you can rely on the results that we deliver. Here are some genuine examples of customer feedback comments which show how our text analysis engine categorises the comments:

So how do we do this so accurately?

Our Feedback Ferret Lexicon Team continually monitors the quality and accuracy of all text analytics results. This is all part of the standard fully-managed service from Feedback Ferret. Unlike most other text analysis tools, our Lexicon team does all the laborious work to ensure you receive highly accurate results. They carry out continuous updates to the text coding and topic definitions and, after each update, all historical data is reprocessed. This ensures that every customer comment in the database is updated to the latest version.

As a result of this human updating of our Lexicon, Feedback Ferret can achieve 93%+ accuracy across the total set of Reporting Topics. This exceptional level of accuracy is typically reached after 2-3 months of a project starting, with numerous cycles of processing, QA and updating.

Our system is programmed to understand the context and make sense of customer feedback even if there are misspellings, grammatically incorrect phrases or sarcastic remarks present. There is no need to correct or update any poor quality original text. Lexicon phrases are compiled using combinations of:-

  • Words – ‘normal’ language words
  • Aliases – accommodating misspellings, synonyms, etc.
  • Stemming – typically used to code for words with a single common stem but with multiple derivatives, e.g.: BUY* codes for BUY, BUYS, BUYING, BUYER, BUYERS, etc.
  • Wild cards – enabling flexible word content within a phrase
  • Emoticons – collections of punctuation with distinct meanings and/or sentiment.
  • Contextual phrases enable the Lexicon to distinguish the difference between the meaning of ambiguous words, as well as false negatives/false positives that typically cause difficulty for automated text analysis.

So if you are looking for a hassle-free, highly accurate solution to analyse your customer feedback comments, look no further. Contact us today.