Parliament Sampo sheds light on a century’s worth of political debates

Parliament Sampo is an open data service, that anyone can use to explore political debate in the Finnish parliament
Illustration of a person speaking on a microphone.
The most vocal member of parliament was Veikko Vennamo with 13,540 speeches. This number is almost double that of the second most talkative member, Erkki Pulliainen. Image: Matti Ahlgren/Aalto University

Researchers from Aalto University and the University of Helsinki have developed an open data service that contains nearly one million speeches held in the Finnish Parliament since 1907. The entire dataset has been compiled into a semantic web that helps researchers, journalists, and citizens understand parliamentary debates.

While the traditional web works with links between webpages, the semantic web works by linking data between webpages, explains Eero Hyvönen, professor at Aalto University's Department of Computer Science and director of the Center for Digital Humanities at the University of Helsinki (HELDIG).

‘Data in the semantic web can be enriched with information from several different sources, which a machine can use to associate individual words to larger contexts and offer it to the user.’

For example, Parliament Sampo can show who most frequently interrupted the Prime Minister Sanna Marin and the Minister of Finance Annika Saarikko during the current term (that would be Ben Zyskowicz). Ahead of the upcoming parliamentary elections in April 2023, citizens may also be interested in what the current representatives from different parties have been speaking about.

‘The easy and open availability of parliamentary discourse increases the transparency of the work of members of parliament,’ says Hyvönen.

According to Hyvönen, the transparency and open availability of the data can affect the way members of parliament speak and how political culture and language is studied.

‘This is a unique project on the Finnish scale, because for the first time we have the entire parliamentary dataset in a machine-readable form,’ says Kimmo Elo, who works as a senior researcher at the Centre for Parliamentary Studies at the University of Turku.

Parliament Sampo uses a machine-readable text corpus called Finparl to offer contextualised information to the user. Elo and senior researcher Jenni Karimäki utilised the same corpus to study how environmental issues have become politicized in parliamentary discourse. They analysed all the speeches held in plenary sessions over the past 60 years and showed a clear increase in the amount of environmental rhetoric. They also found changes in the manners of speaking that have received less attention in previous research.

‘Parliamentary speeches are particularly important research material because they represent contestation for political alternatives,’ says Elo. ‘In environmental issues, the discourse of the major parties has varied between national-conservative values and green-liberal values. For example, the agrarian Centre Party has been quite green in their discourse on agricultural issues, but conservative in how they have spoken about energy and nature conservation policies.’

The Sampo model makes data accessible to everyone.

Hyvönen leads the semantic computing research group at Aalto University. The group has been developing various Sampo services for years, with the aim of providing essential national data sets to researchers and citizens. A prominent example is War Sampo, which compiles material related to military and political events of the Winter and Continuation Wars. The service has already been used by more than a million people.

‘War Sampo automatically reconstructs individual war stories by linking materials from the National Archives of Finland, the Finnish Defence Forces and other data providers,’ says Hyvönen, who was awarded the State Award for Public Information in 2014.

The idea of the Sampo model is to combine data from different databases into a single place where information can be easily searched, analysed and visualised. Parliamentary speeches were digitised and available before Parliamentsampo, but studying the entire corpus was very manual and without the added benefits of automation.

‘Our work represents a paradigm shift in the way humanistic data is published and studied,’ says Hyvönen. ‘After the rise of printed text and the internet, we are now in the third transformative phase where linked data and the tools and applications of artificial intelligence are becoming possible.’

Eero Hyvönen

  • Published:
  • Updated:

Read more news

Photo: Tima Miroschnichenko, Pexels.
Press releases Published:

In low-hierarchy organisations, even key policy issues are discussed in Slack

In a recent study, Aalto University alumn Lauri Pietinalho, a visiting scholar at New York University's Stern School of Business, and Frank Martela, an assistant professor at Aalto University, investigated how low-hierarchy organisations deal with shared policies in confrontational situations and how authority functions within them.
bakteereja ohjataan magneettikentän avulla
Press releases, Research & Art Published:

Getting bacteria into line

Physicists use magnetic fields to manipulate bacterial behaviour
border crossings 2020
Press releases, Research & Art Published:

Nordic researchers develop predictive model for cross-border COVID spread

The uniquely multinational and cross-disciplinary research was made possible by transparent data-sharing between Nordic countries.
insole at pdp gala
Press releases, Research & Art, Studies Published:

Compostable wood foam replaces plastic in shoe insoles

Aalto University students develop prototype of durable wood-based insole – Finnish shoe company starts testing material on users this autumn