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.
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%.
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.
Wonderflow empowers businesses with quick and impactful decision-making because it helps automate and deliver in-depth consumer and competitor insights. All within one place, results are simplified for professionals across any high-UGC organization, and department to access, understand, and share easily. Compared to hiring more analysts, Wonderflow’s AI eliminates the need for human-led setup and analysis, resulting in thousands of structured and unstructured reviews analyzed within a matter of weeks and with up to 50% or more accurate data. The system sources relevant private and public consumer feedback from over 200 channels, including emails, forums, call center logs, chat rooms, social media, and e-commerce. What’s most unique is that its AI is the first ever to help recommend personalized business actions and predict the impact of those actions on key outcomes. Wonderflow is leveraged by high-grade customers like Philips, DHL, Beko, Lavazza, Colgate-Palmolive, GSK, Delonghi, and more.
Other articles you might like:
Product Development · Sep 12, 2022
Proper Review Analysis: How to Analyze Customer Reviews (+ Examples)
It’s pretty difficult to imagine a world without reviews. Not many of us walk into a shop and make a purchase without browsing at least a handful of online reviews beforehand. In fact, a study from TrustPilot found that almost 9 out of 10 customers consult online reviews before buying. Though these reviews are incredibly helpful to consumers, for business owners, trying to use reviews to guide the product development process or improve the customer…
Marketing · Aug 25, 2022
More Smiles, More Stars: 10 Examples of Leveraging Positive Customer Reviews
Brands know that reviews are everything. Whether they are positive, negative, or neutral, customer feedback is at the core of any business. It’s a matter of how well your company leverages or responds to each type. For instance, positive customer reviews are just as powerful of an influence on business success, if not more, than negative ones. And do you just simply smile when you see a customer’s compliment? Of course not! You may want…
Utility & Energy · Aug 09, 2022
More Than Another Bill: Why VoC Programs Improve Utility CX
When did your utility provider last ask you to rate your customer experience (CX) with them? With rising competition, energy costs, customer demands, and regulatory and stakeholder pressure to improve customer services, these key factors drive service providers of water, electricity, and gas to engage deeply with their customers. Old traditional business models must be changed to adapt to the times, and utility brands must prioritize CX more than ever before. The Utility Customer Experience …