Public space reports

Municipality of Hilversum

If something needs to be fixed or cleaned up on the street or in a park, it can be reported to the municipality through Signals, the open source notification system of for and by municipalities.

Last change on 22nd of November 2024, at 15:05 (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
• Nature and Environment

Begin date

2024-07

Contact information

[e-mail]

Link to publication website

https://meldingen.hilversum.nl/

Responsible use

Goal and impact

If something needs to be fixed or cleaned up on the street or in a park, it can be reported to the municipality through Signalen, the open source reporting system of for and by municipalities. A dangerous traffic situation, housing nuisance or nuisance from people and the hospitality industry can also be reported. Previously, people had to choose which category their report best fitted with (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 notifications. Therefore, we now use an algorithm that recognises words, e.g. 'rubbish' and 'pavement'. Based on this, it determines which category the report best fits and which department should handle it. So the caller no longer has to choose a category, and the call is handled faster because it goes to the right department.

Considerations

Field not filled in.

Human intervention

All reports categorised with less than 40% certainty are forwarded to the Customer Contact Centre. A human assessment then takes place and the call is still categorised. Reports that are wrongly forwarded to an incorrect category are also manually placed in the correct category by the department responsible (sometimes via the Customer Contact Centre).

Risk management

There are few risks in this algorithm. It places a notification in the right category and gets it to the attention of the right department faster. If the algorithm cannot place a notification in a category with sufficient certainty, it ends up in the 'Other' category. Employees at the Customer Contact Centre review those calls and manually put them in the right category. So if the algorithm does not work properly, it takes a little longer for the report to reach the right department. The reporter can add personal data if he or she wants to be kept informed. This data is stored securely and not used by the algorithm.

Operations

Data

Notifications

The dataset consists of notifications made previously (free text field). Initially, we used 100,000 notifications from past years to train the algorithm. It is regularly retrained with new notifications and implemented corrections to existing notifications. If the Customer Contact Centre or departments see an incorrect categorisation, (see Human monitoring) they correct it manually in the notification system. These corrections are used in retraining.

We cannot disclose this dataset in this register. Because the data comes from a free text field, it may contain personal data, although this is not explicitly requested.

E-mail address and phone number for follow-up questions

Someone making a report can leave their phone number and/or e-mail address if they want. We then keep the reporter informed of the progress and we have the option to call him or her back. This information is not kept longer than necessary for this purpose and is not used by the algorithm.

Links to data sources

Privacy verklaring gemeente Hilversum: https://hilversum.nl/privacy/privacyverklaring-gemeente-hilversum

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, logistic regression (a machine-learning technique) is then used to determine which category the report belongs to and thus which department within the municipality the report is most likely to fit.

Link to code base

https://github.com/signalen