Public space reports

Municipality of Bergen op Zoom

If something needs to be fixed or cleaned up on the street or in a park, it can be reported to the municipality through the online notification system.

Last change on 15th of July 2024, at 12:44 (CET) | Publication Standard 1.0

• Publication category: Other algorithms
• Impact assessment: Field not filled in.
• Status: In use

General information

Theme

• Public Order and Safety
• Space and Infrastructure

Begin date

3-2022

Contact information

https://www.bergenopzoom.nl/contact-en-openingstijden

Responsible use

Goal and impact

Previously, people had to choose which category their report fit best (e.g. 'nuisance' or 'street furniture'), so that the report went to the right department in the municipality. But the municipality is a complex organisation and the list of categories is long. As a result, people did not always choose the right category. This sometimes caused delays in processing reports. So now the reporter no longer has to choose a category, and the report is processed faster because it goes to the right department.

Considerations

Previously, citizens had to specify which department the report was for, which regularly resulted in reports ending up in the wrong department, causing delays in resolving reports.

Human intervention

If the algorithm can link a notification with less than 40% to a department, it is placed in the 'Other' category. Notifications in this category are manually assigned to the correct department. If a call still ends up in the wrong department, it can always be forwarded manually to the correct department.

Risk management

The risk is seen as zero, as notifications can still be forwarded manually to the correct department

Legal basis

Municipal Act

Operations

Data

Only if the citizen chooses to leave his/her phone number and/or email address when making a report. This data is only used to provide feedback on status changes of the notification and is not used for any other purposes.

Technical design

Architecture of the model The text of the notification is divided into individual words. Each word from a notification is analysed to see how unique it is to that notification, set against the total collection of words ('TF-IDF' or 'term frequency-inverse document frequency'). As a result, a word like 'the' or 'thank you' gets a low weight and a word like 'rubbish' gets a higher weight. From that combination of words, it is then determined which category the notification belongs to and thus which department within the municipality the notification is most likely to fit.