Personenvaak

Personenvaak is a term used in data analysis and social science to describe a frequency-based metric that measures how often individuals are represented in a dataset, content corpus, or stream of events within a specified time window. The word is a Dutch compound of personen (people) and vaak (often, frequently). While not widely standardized, personenvaak is used to discuss the visibility or presence of people across items such as articles, posts, or records.

Calculation and interpretation

In a given dataset, for each person p, a raw count c_p denotes the number of items in which p appears. The frequency f_p can be defined in several ways, commonly as c_p / n, where n is the total number of items, or as c_p / T in a time-bounded analysis, where T represents the number of time units considered. Aggregated metrics include the average frequency across all persons and the distribution of frequencies to reveal concentration or dispersion of representation.

Applications

Personevaak can be applied in media studies to assess the visibility of public figures, in social media analytics to gauge exposure of individuals, and in historical or corpus-based research to study representation and bias. It can support comparisons between datasets, time periods, or domains (for example, comparing coverage of different subjects or demographics).

Limitations and considerations

Accurate calculation depends on reliable person identification and name disambiguation. Variability in item length, coverage, and time window selection can significantly affect results. Privacy concerns may arise when tracking individuals, especially in small or sensitive datasets. As a metric, personenvaak is best used in conjunction with qualitative analysis and other representation measures.

See also: representation bias, exposure metrics, frequency analysis, data representation.