Follow our journey

Evaluating Text Mining Algorithms Part II

In our previous blog, we stressed the importance of precision and recall when evaluating text-mining algorithms. In this blog, we will put two existing text-mining tools to the test. Precision, recall, F-measure? But first, a short recap of precision and recall. Precision is the percentage of the retrieved results that are relevant. Recall is the […]

Text Mining Algorithms Part III: Evaluating CV Parsers

This is the final part of our three part series on text mining. In the first two parts, we explained precision and recall and presented the test results of two generic text mining tools by TextRazor and Lexalytics. In this blog we will put two specialised text mining tools to the test, namely two CV […]

Improved job search user experience on the VDAB website

At theMatchBox we notice immediately when a search or match function of a company website is in need of improvement. Being particularly familiar with the HR-industry we didn’t miss the fact that VDAB’s (the Flemish public employment service) search function for their popular job search database wasn’t up to par. For example, when searching for […]

Evaluating Text Mining Algorithms, Part I

More and more people are getting aware of the importance of storing their data. Quite often this big pile of data is called a gold mine with hidden treasures, from which we can derive new insights or even new products. The only thing we have to do is to start mining. Thankfully, quite a lot […]