Your questions answered

What is Text Mining?
Text mining is the term used to describe the process by which important information can be found within documents in an electronic format using computer technology. In much the same was a person may read a newspaper and pick out salient facts, opinions, and inferences, we emulate this process using computer coding based on rules and algorithms.

Isn’t that just data mining?
Indeed it is quite similar and a good way to look at text mining in the first instance is to consider data mining but instead of extracting numbers and values we are extracting words and phrases. This is actually very important because the data normally tells you when some process or another is working/not working but it is the written text that accompanies the data that actually tells you about the root cause.

What’s the difference between data mining and text mining?
As mentioned above there is a simple distinction that helps conceptualise text mining but in reality the difference somewhat more blurred particularly when comparing the data mining principles as opposed to generalities. This is because both text and data mining are underpinned by similar methods of analysis to identify patterns and discover new information. Indeed you may sometimes even hear the term “text data mining” used to describe our work.

What kind of businesses would benefit from text mining?
Almost everybody! Pharmaceutical/Healthcare, Software/IT, Business Intelligence, Retail, and Engineering are just some of the sectors in which we operate. If you are faced with reading a daunting number of documents in order to find some key information then you are very likely to benefit from text mining. We help our clients find trends in Patent literature, interrogate social media to gain insight into patient reported symptoms of diseases, identify key issues from improvement/customer satisfaction from call centre logs and surveys, and generally take the chore out of manual information extraction.

What else is text mining known as?
Text mining may also be referred to as Natural Language Processing (NLP) or computational linguistics. It encompasses a multitude of disciplines, skills and components that you may come across from time to time such as machine learning, parsing, ontologies and dovetails with wider themes such as text analytics, big data, deep learning, and artificial intelligence (AI).

Do you have a demo of the software?
Yes, a demo of our web interface where you are able to view the results of the text mining is available here.

In the demo we have processed over 2 million tweets on the subject of Fintech, Legaltech and contract analytics from which we have text mined results that refer to emerging technology and innovation in these sectors. Please complete our contact form and we will provide a full demonstration.

I can get what I need from a Google search!

Let’s not forget Google only surfaces the links it knows about, granted this is a vast amount but not everything.

Crucially Google does not read the content of every web page but instead uses meta data for indexing.  We read the content so it is very easy indeed for Google to miss a page that talks about innovation in the pet industry for instance that does not use these terms in the meta data.  Let me ask you does Google know printedelectronics is a huge topic in smart packaging?