This dataset contains network embeddings of all individuals who are registered in the Basisregistratie Personen (BRP) on January 1st YYYY and part of at least one population network file, i.e., BURENNETWERKYYYYTAB, COLLEGANETWERKYYYYTAB, FAMILIENETWERKYYYYTAB, HUISGENOTENNETWERKYYYYTAB, KLASGENOTENNETWERKYYYYTAB. All network datasets from the same year were concatenated and duplicate relations between every pair of individuals removed. The network was made symmetric by adding missing reciprocal relations. The resulting undirected and unweighted network was used to create the embeddings. Network embeddings are numerical representations with a fixed number of dimensions that encode the position of an individual in the network. The embeddings in this dataset were created using the LINE algorithm and have 16, 32, or 48 dimensions. The algorithm predicts whether two nods are connected in the network or randomly paired. It was trained for 5 epochs, i.e., it iterated over all relations in the network 5 times. The first half of the dimensions (i.e., dimensions 0-7, 0-15, and 0-23) contain first order embeddings reflecting location in the network. The second half contains second order embeddings reflecting similarity in local neighbourhood. The embeddings in this dataset were transformed using the DINE algorithm that forces the embedding dimensions to become more sparse and more orthogonal to each other. The dataset files follow the schema NETEMBEDLINEDINEYYYYDIMXXX where DIMXXX refers to the number of dimensions.

This dataset is only available under strict conditions within the Microdata Environment at CBS. Since this is a project-generated dataset made available for reuse via the CBS Data Storage, access to the following source CBS files has to be requested:

Burennetwerk    2020-2022
Colleganetwerk  2020-2022
Familienetwerk  2020-2022
Huisgenotennetwerk  2020-2022
Klasgenotennetwerk  2020-2022

(see full list under "Data Source"). Read more about the conditions to access and use the CBS data: www.cbs.nl/nl-nl/onze-diensten/maatwerk-en-microdata/microdata-zelf-onderzoek-doen.

The dataset contains the following variables:

RINPERSOONS: Samen met RINPERSOON identificeert dit nummer de persoon (String): De bron waaruit een persoon identificerend nummer is afgeleid RINPERSOON: Samen met RINPERSOONS identificeert dit nummer de persoon (String): Dit nummer identificeert een natuurlijk persoon. Het is een betekenis- en dimensieloos nummer. DIMXXX: Embedding dimension XXX (Numeric): Abstract number that encodes an individuals position in the network. The number can be positive or negative and is centered around zero. The dataset can contain between 16 and 48 columns of this type.