Randanteckningar om svensk mediepolitik 1920–1970

Ur temamodellering av 11 000 riksdagsprotokoll

Abstract

In an explorative manner, this article uses a data-driven digital history set-up to focus on how the Swedish Riksdag, its political parties and parliament members discussed media issues. By distant reading and topic modeling a dataset of more than 11,000 parliamentary minutes – approximately 400 million characters – the article gives a new perspective of Swedish media history in general and national media politics in particular. The article uses the computational method topic modeling to study latent themes or discourses in the dataset (by accentuating words that tend to co-occur) that together create different topics. The article includes a number of media historical observations and findings, and the frequent graphs also display interconnections between different media topics, as well as other societal topics that media were related to.