How good are humans in text analysis?

Published on — Written by Wonderflow

how good are humans in text analysis - wonderflow

Accuracy is a measure of the capability of technology to interpret a text correctly. Some companies claim the accuracy of their technology is 99%, is that even possible? In today’s video, we are going to refute some myths about text analysis, and we are going to discover the best way to achieve a high level of accuracy.

Today’s video is very different from the other ones because for the first time I talk about Data science. I think there is a lot to do in terms of education, and I hope you will find it very interesting.

I have been leading a data science company for some years now and I was able to put together a list of interesting questions that I am usually asked. Today’s question is: How good are humans at text analysis? Or I could say it differently: what is good accuracy in text analysis?

First things first. What is the accuracy?

Accuracy in our case is a measure of the capability of technology to interpret a text correctly. Correctly means that this software is able to identify which are the topics mentioned by the author of the text, and evaluate whether their sentiment is positive or negative. To evaluate whether the analysis is correct or not, it’s scientifically recommended to have the same dataset manually analyzed by a group of humans. Keep in mind that the bigger the group, the higher the scientificity of the measurement.

Let’s get back to us….If you search the web for text analysis or sentiment analysis software you will probably find very catching advertisings where companies claim the accuracy to be 99% or something like that. Let me tell you one thing…you will never get anywhere close to 99% accuracy, independently from the software that you will use.

Why do I say that you won’t get this accuracy?

Number one: technology is not good enough yet

Number two: humans disagree with each other too often

Let’s start with the first reason, which is less intriguing from a psychological perspective but straightforward to explain. Today’s analysis technologies are good, but not good enough to interpret free texts as you may expect. Most analysis technologies are based on statistical algorithms, like the ones that drive a driverless car. These algorithms work well when they can be trained on very large datasets, I am talking about millions of records. A driverless car collects billions of information each minute it drives around, therefore it’s just perfect for this type of technologies. At the same time, it is unlikely to collect enough texts about a certain topic to train that statistical algorithm for text analysis. So, surprisingly, it is easier to drive a driverless car than to analyze a text…can you believe it?

On the other side, we have rules based algorithms. These ones use predetermined interpretative rules written by humans. What is it? Basically, an analyst teaches the technology how to interpret a sentence, and then another one and so on. So, in this case, the technology doesn’t learn from large datasets but from single, but precise, that commands from a human. As you can imagine, this technique is very time consuming but as of today it is the most accurate one. Am I saying 100% accuracy or so? No, but 90% is feasible and it’s already a very good result.

Let’s now move to the more philosophical reason why you won’t get 99% accuracy: humans disagree with each other too often

I have recently read an experiment conducted by the University of Pittsburgh. It’s called Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis. I really recommend you to read it, it’s online and it’s free. What did they do? They wanted to understand how good were humans in interpreting texts, and we can then compare it to the accuracy of our technologies.

In short, they had a group of humans analyzing the same records, and they found out that, they agree with each other 82% of the time. They literally say that “Human analysts tend to agree 82% of the time, which means that they will always find documents on which they disagree with the machine on”. Let me explain this in simple words, if two people read the same text and the text contains one hundred different topics, these two people will only have 82 topics in common, and would disagree on the remaining 18.

What does it mean from a statistical perspective? It means that moving from 80 or ninety percent of accuracy to 100% would be almost impossible even with the best algorithms, but even if one day we reach that impressive level of accuracy, we will always have more or less 18% of our colleagues thinking that we are wrong.

Very long story short: machines, with the help of humans, can reach levels of accuracy, above 90%. Humans alone hardly go above 80 percent. What’s the lesson learned? We are worse than what we think.

Read more about NLP, the technology that substitutes humans in text analysis, here.

About Wonderflow

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.

Start making winning decisions based on customer feedback todayGet a free demo

Other articles you might like:

wonderflow image

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…

utility cx

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 …

Ron Jacobs Philips Brand Licensing

Interview · Aug 03, 2022

Customer-Centricity in Consumer Electronics: VoC Interview with Ron Jacobs, Philips Brand Licensing product professional

As part of our Voice of the Customer (VoC) interview series, Stefano Pecorari, Client Success Director at Wonderflow, welcomes Ron Jacobs, Brand Licensing product professional at Philips. Philips is a Dutch multinational founded in 1891 as a lighting company and later expanded to medical equipment, consumer electronics, and domestic appliances. The company is headquartered in Eindhoven. Later, it moved to Amsterdam in 1997. Nowadays, Philips is focused mainly on the health tech continuum. Its mission is…