In this video, our CEO explained how good are humans in text analysis. Recently he has been speaking about machine learning, and why it’s not such a great solution for natural language processing. So he decided to make this video, where he explains which are strengths and limitations of us, humans, when we perform the job manually.
We have seen many brands still doing this internally, so we believe it makes a lot of sense to share our point of view on this matter.
Usually, companies that sell products and services to a large number of individual customers, receive a huge amount of feedback. Online reviews, customer service data or open answers to the NPS surveys are common sources of feedback. If properly analyzed, this feedback can deliver the most valuable insights. For this reason, brands start to analyze these texts, and many of them don’t use natural language processing or other technologies, but they try to do it manually, using manpower.
So what are the pros and cons of running manual text analysis? Let’s start with the good things:
Number One. Easy to start. In fact, starting a human analysis is quite simple. Once we agree on the dictionary and the topics that we want to research, we just need to start reading and write down the annotations
Number Two. Easy to reach good quality. If it’s easy to get started, it’s also easy to reach good quality. In theory, we could reach high accuracy from the very first record that we read. Why? Because our interpretation capabilities have been trained during our life, day by day. This means that we don’t need training datasets. We also know the lexicon and the grammar, therefore we don’t need to create our own linguistic rules.
Number Three. Identify anomalies. We are much better than the machines in identifying anomalies, such as irony for example.
Have a look at our next post to find out the main disadvantages of human analysis.
