Visualizing citizen signals during COVID-19

by Ana Milicevic

Visualizing citizen signals during COVID-19

by Ana Milicevic

by Ana Milicevic

How do municipalities get a grip on the new reality and the changing digital feedback?

COVID-19 has significantly shaken up the way many service providers work, especially communication with the customer. That is no different within the government. In fact, the services provided by, for example, a municipality run entirely in one go via the internet and the telephone, where previously many desk visits took place. The contact with the citizen thus feels like lost at once, the desk clerk was one of the important feelers for the citizens and what lives with them.

The type of questions as a result of the corona epidemic has also changed in recent times: of course (new) questions about COVID-19 itself are frequently asked, but also questions about subjects such as permits, benefits and the various support measures from the government. And the feedback is also created in various ways by means of call-back notes, audience reactions, complaint forms, question suggestions, (e-mail) notifications and customer feedback in the form of NPS.

Citizen experience

In order to get a grip on this change, a strong need has arisen to be able to bundle citizen signals from various contact channels, to easily understand what these (new) citizen signals are about and to learn where the municipality can do better in its (digital) services . This applies to all parts of the municipality, whereby prioritization based on these expressed wishes is the next step in improving the citizen experience from the municipality. Examples of this are improving the need for information provision regarding certain topics or insight into types of actions to improve the sentiment of customers about the service provision. In other words, as a municipality, they would like to gain insight into the most important issues affecting citizens and the associated actions in specific areas. These are often grouped around the following municipal topics.

Municipal subjects

  • Building and Renovation: everything that has to do with building, permits, remodeling
  • Care and Support: everything that has to do with WMO (Social Support Act)
  • Parking: parking often appears to be a separate theme within the various sources. What about the availability and accessibility of a parking space? And do people experience nuisance with parking / parking users?
  • Safety: safety as an overarching spearhead within the municipality. Here the focus is on security in various areas: on the street, in traffic, in the house (burglary). In addition, the ‘feeling’ of the residents plays a role, to what extent do they feel safe?
  • Transport: can citizens move easily within the municipality?
  • Cleaning up and Waste: how do the residents of the municipality experience the maintenance of the environment and any associated nuisance regarding waste?
  • Service provision by the municipality: how is the service provided by the municipality? And how do citizens subsequently experience this service?
  • Housing / life: matters related to the daily life of the residents of the municipality. Think of liveability within the neighborhood / municipality, (financial) solutions for personal situations.


The Underlined text mining solution for municipalities brings together feedback data from different sources. All (unstructured) texts are converted into clear categories that are often related to the aforementioned topics. Thus, key terms are automatically extracted from all feedback texts so that the main points are quickly identified.
Data sources can be very diverse, such as telephone notes, public reactions, complaints, question suggestions, reports, requests, but also feedback and satisfaction data.

To get started with the solution, you can visualize the results in a dashboard with which you can view KPIs, insights and trends yourself (such as the above visualization). You have a direct overview of all signals on one main screen, including the (text mining) results. In addition, you can delve deeper into a specific data source or text mining category at the touch of a button. In this way it is immediately clear where the greatest opportunities lie and where action can be taken.

Analytical model

Topics and subtopics are assigned on the basis of the open texts. In this way the possibility arises to gain insight from all these open texts. Open texts that are usually very valuable, because here the customer often indicates where the municipality can really improve or where things are going well (this in an uncontrolled way).

The analytical model provides the following information:

Taxonomy specifically trained on all data sources within the municipality with a:

  • Main category, possibly several per line.
    For example: “employee attitude and behavior”
  • Subcategory within the main category, possibly several per line.
    For example: “empathy”
  • Sentiment analysis per line

Learn more

Interested in a no-obligation discussion about what this can mean for your municipality? Please contact
Marcel van der Marck, Sales & Business Development Director at Underlined.

T 06 81820953

Leave a Reply

Your email address will not be published. Required fields are marked *