Market Research

What is the accuracy in text analysis

Published June 19, 2019·Written by Wonderflow

what is accuracy in text analysis - Wonderflow

Probably, the most frequent question about text analysis is “what is the accuracy?”. So, today we will tell you what to measure in order to determine the quality of your analysis.

Let’s start by saying that what we usually call accuracy in text analysis, is the mix of two main indicators, called precision and recall.

Recall

In simple words, the recall in text analysis measures how many times the system is able to identify a specific topic from an unstructured text, over the total amount of times when the topic is really mentioned in that text.

Imagine a random text where the author talks about the Sun in 10 different sentences, plus some other sentences about the moon and some others about Mars. Suppose that a text-analysis algorithm designed to identify expressions related to the Sun extracts 7 expressions from that text, of which only 5 of them are really related to the Sun. In that case, its recall is 5 out of 10, which means 50%.

Precision

On the other side, Precision measures how many times the system has identified a topic correctly, amongst all the times that topic has been identified by the system itself.

Suppose a random text where the author talks about the Sun in 10 different sentences, plus some other sentences about the moon and some others about Mars. If a text-analysis algorithm tries to identify expressions related to the Sun, extracts a total of 7 expressions from that text, whether only 5 of them are really related to the Sun, and the other two to the moon, its precision would be 5 out of 7, which means approximately 70%.

To sum it up, we can consider accuracy as a score derived by the capability of the machine to extract topics from a given text, and its ability to make sure many of these extracted topics are correct.

If you want to know how good are humans in performing text analysis, watch this video.

Share this post:

Other articles you might like:

wonderflow image

Marketing · Sep 03, 2021

MarTech: The Rise of Marketing Technology Investments & 7 Key Marketer Tools In 2021

The global MarTech landscape is fast evolving. But what does that really mean? Find out here what is MarTech, including key trends to consider before making new marketing technology investments. Plus, 7 key solutions in 2021 for every ‘marketer stack’ to conquer CX.   The global MarTech landscape is continuously evolving, making decision-making more challenging for marketers. Because of this, modern companies must ensure that they are investing in the right marketing technology solutions that…

wonderflow image

Customer experience · Aug 26, 2021

Stay Connected: How To Be Customer Centric In Telecommunication

  As a telecommunication service provider, you may have been thinking your team has worked hard to satisfy your customers – until one day you see another service cancellation request by another customer. Worse, a low-star rating of your business.  And like many other telecom carriers, you may wonder why this is the case? Aren’t we living in the age of digital transformation where we basically would all die without WiFi? Why are telecoms increasingly…

wonderflow image

Business · Aug 31, 2021

Guest Blog: Advances In AI Will Transform Sentiment Analysis

HIPSTO has developed a premier AI open knowledge discovery platform. As one of our technology partners, their advanced natural language understanding technology works within Wonderflow’s advanced voice of the customer analytics platform to provide users with the most reliable and accurate results. In their guest blog post, HIPSTO helps CX professionals to gain a clearer understanding of what sentiment analysis is, including key challenges in this exciting and emerging research field. Plus, 5 key benefits…