The technology uses supervised ML techniques to improve the analysis of qualitative feedback data with labelling and categorisation. 

The tech takes historical data – in this case any labelling or categorisation the user has previously inputted into the software – and predicts how the feedback should be categorised based on that data.

The algorithms look at different variations and combinations of the wordings and other known data such as answer options in the feedback survey and the URLs where the feedback was collected.

Kees Wolters, co-founder and managing partner of Mopinion, said: “By applying machine learning techniques, we are essentially removing the burden for users of having to filter through high volumes of feedback and monotonously label individual feedback items. This not only makes the categorisation process effortless, but also reduces workload and increases efficiency.”

The automatic feedback categorisation technology is the first of several new, built-in technologies Mopinion plans to launch. This release is the predecessor of an ‘unsupervised’ machine learning technology that will be introduced later this year.