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.

Text classification for undermining themes

This is a set of models that can assess texts. Based on the text in a registration, they determine whether it is about a particular topic of undermining. The outcome of the model is used to organise the work of police officers.

Last change on 13th of May 2026, at 11:50 (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

Begin date

2023-12

Contact information

https://politie.nl/

Responsible use

Goal and impact

A group of police staff review and assess registrations from police systems.

The police use keywords to find these registrations. But keywords do not always find the right registrations.

Therefore, the police use a model that reviews and sorts texts. This model has learned from what police staff find relevant or not.

This allows staff to work faster on the most important registrations.

Considerations

Without this sorting, police staff would spend a lot of time reading records that are not important.

Human intervention

The police officer decides which registrations to review. The model only helps with sorting.

Risk management

Users can turn off the AI suggestions if they want.

With the outcomes, the model provides explanations, with a technique that shows why something was judged as it was.

There is also a list of words that should not be used. These words are not included in the model, for ethical reasons.

The model is re-trained regularly. This way it stays current and works with recent information.

We keep track of which model made a prediction, so this can always be reflected.

Operations

Data

The model uses text from the Basic Enforcement Facility (BVH).

Technical design

The model learns based on examples assessed by police officers. This is called 'supervised learning'.

The input is text from registrations. The output is an assessment: does this registration belong to a particular topic or not.

Similar algorithm descriptions

  • 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 25th of January 2024, at 12:18 (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 25th of January 2024, at 12:17 (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
  • 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 25th of January 2024, at 12:16 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use