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.

Anonymise

Based on language technology, personal and company names are read and filtered out of text files such as emails and individual documents.

Last change on 20th of March 2025, at 14:50 (CET) | Publication Standard 1.0
Publication category
Other algorithms
Impact assessment
Field not filled in.
Status
In use

General information

Theme

Organisation and business operations

Begin date

10-2024

Contact information

info@pzh.nl

Responsible use

Goal and impact

Support in the review process where legal protection applies to information disclosed. Protection of the grounds for exception set out in the AVG and Woo legislation, such as privacy-sensitive personal and business data

Considerations

Manual review is intensive and error-prone. A suggestion list from the entity extraction algorithm captures all conceivable instances of individuals in the text.

Human intervention

Within the software, a list is built and offered to the user to select in the automatic varnishing process. The choice to adopt an advised term as a person name and not disclose it is up to the user who makes a decision on this based on the context.

Risk management

There is no risk of automated decision-making and the algorithm has no impact on fundamental rights because the algorithm does not make decisions with legal consequences. It only suggests anonymising personal data. In doing so, the algorithm provides precisely for the protection of fundamental rights. The Province employee always does the final check whether a document is correctly anonymised.

Legal basis

Legislation around public access to government data (Woo)

Links to legal bases

Wet open overheid: https://wetten.overheid.nl/BWBR0045754/2023-04-01#Hoofdstuk5

Operations

Data

This concerns documents as named in the Woo and messaging information within the Province. Including email, files, Whatsapp messages and other media in which administrative decision-making can be found.

Links to data sources

Algemene Office applicaties: Dit betreft standaard Office formaten inclusief email en social media formaten.

Technical design

Texts are recognised on the basis of Named Entity Recognition (NER) and a process within Insights extracts the names for further processing towards the management interface and the automatic lacquer rules.

External provider

ZyLAB eDiscovery & Compliance Services B.V.

Similar algorithm descriptions

  • Based on language technology, personal and company names are read and filtered out of text files such as emails and individual documents.

    Last change on 14th of October 2024, at 10:47 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    Field not filled in.
    Status
    In use
  • Based on language technology, personal and company names are read and filtered out of text files such as emails and individual documents.

    Last change on 5th of February 2025, at 9:14 (CET) | Publication Standard 1.0
    Publication category
    Other algorithms
    Impact assessment
    DPIA
    Status
    In use
  • Among other things, the algorithm recognises and anonymises (personal) data, confidential financial data and other privavy sensitive information in documents before they are published or shared.

    Last change on 7th of November 2024, at 10:08 (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 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