Please note: The algorithm descriptions in English have been automatically translated. Errors may have been introduced in this process. For the original descriptions, go to the Dutch version of the Algorithm Register.

Public space reports

The reporting system's algorithm recognises words in reports, such as 'rubbish' or 'pavement', and automatically determines the correct category and department. As a result, reporters no longer have to choose a category, and reports are dealt with faster at the right department.

Last change on 7th of January 2025, at 13:02 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
DPIA
Status
In use

General information

Theme

  • Public Order and Safety
  • Space and Infrastructure

Begin date

Okt-23

Contact information

datashop@denhaag

Link to publication website

https://denhaag.dataplatform.nl/#/data/1ffa4758-d143-4d78-b510-a713ab8365df

Responsible use

Goal and impact

The aim of the algorithm in Signals is that reports (made to the municipality) are immediately registered in the correct category. The list of categories that can be reported to the municipality is extensive and not clear for reporters from outside the organisation. Based on the report text, the algorithm estimates the correct category of the report. This eliminates the need for human intervention to get reports to the correct handling teams.

Considerations

There are few risks in using this algorithm and it has added value for citizens and employees handling reports. This algorithm was technically adopted from the municipality of Amsterdam. We like to do our developments through the community principle where we prefer cooperation with other municipalities to self-construction. We chose common ground, the architecture for cooperation.

Human intervention

If the algorithm cannot find an appropriate category based on the text written by the notifier, the notification is put on the "other" category by the algorithm. A human assessment then takes place and the notification is still assigned to an appropriate category.

Risk management

There are few risks associated with this algorithm. The dataset used to train the algorithm is based on report descriptions made by reporters in the past. Reporters can write any information they want in this text, which could contain personal data.

Legal basis

  • Municipal Act
  • General local regulation
  • Liquor and Catering Act
  • Roads Act
  • Noise Pollution Act
  • Soil Protection Act
  • Environmental Protection Act
  • Housing Act
  • Town and Country Planning Act
  • Nature Conservation Act
  • Flora and Fauna Act
  • Attractions and Games Equipment Act Decree

Impact assessment

Data Protection Impact Assessment (DPIA)

Operations

Data

Training is based on the text of old reports about the city, without contact details. For each new training, the dataset is expanded with the "latest" set of report texts with the appropriate categories linked to them.

Technical design

The text of the notification is broken down 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.

External provider

Open Source

Link to code base

https://github.com/maartensukel/example-textual-classification-citizen-reports

Similar algorithm descriptions

  • The algorithm in the software recognises and anonymises personal data and other sensitive information in documents. Governments regularly publish information related to the drafting and implementation of their policies (e.g. based on the Woo). This tool is used to render sensitive data unrecognisable in the process.

    Last change on 9th of January 2025, at 9:23 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use
  • The algorithm in the software recognises and anonymises personal data and other sensitive information in documents. Governments regularly publish information related to the drafting and implementation of their policies (e.g. based on the Woo). This tool is used to render sensitive data unrecognisable in the process.

    Last change on 20th of November 2024, at 14:27 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use
  • The AP uses this algorithm to classify data breach reports by severity. Based on that classification, inspectors can prioritise serious reports. The algorithm does not contain any personal data.

    Last change on 11th of October 2024, at 9:33 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • The algorithm recognises (personal) data and otherwise confidential information in a document and makes a proposal to anonymise it. A staff member evaluates the proposal and makes the final adjustment, making the document suitable for publication.

    Last change on 7th of October 2024, at 15:33 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • The algorithm recognises (personal) data and otherwise confidential information in a document and makes a proposal to anonymise it. A staff member evaluates the proposal and makes the final adjustment, making the document suitable for publication.

    Last change on 16th of August 2024, at 8:50 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use