Browsing by Subject "topic modelling"

Sort by: Order: Results:

Now showing items 1-5 of 5
  • Isoaho, Karoliina Laila Hannele; Moilanen, Fanni Sofia; Toikka, Arho Ilmari (2019)
    The Energy Union, a major energy sector reform project launched by the European Commission in 2015, has substantial clean energy and climate aims. However, scholarly caution has been raised about their feasibility, especially with regards to accommodating climate objectives with other closely related yet often competing policy goals. We therefore investigate the policy priorities of the Energy Union by performing a topic modelling analysis of over 5,000 policy documents. A big data analysis confirms that decarbonisation and energy efficiency dimensions are major building blocks in the Energy Union's agenda. Furthermore, there are signals of policy convergence in terms of climate security and climate affordability policies. However, our analysis also suggests that the Commission is not actively prescribing trajectories for renewable energy development or paying close attention to declining incumbent energy generation technologies. Overall, we find that the Energy Union is not a 'floating signifier' but rather has a clear and incrementally evolving decarbonisation agenda. Whether it further develops into an active driver of decarbonisation will largely be determined by the implementation phase of the project.
  • Anttonen, Markku; Lammi, Minna; Mykkänen, Juri; Repo, Petteri (2018)
    The Triple Helix concept of innovation systems holds that consensus space among industry, government and university is required to bring together their competences to achieve enhanced economic and social development on a systemic scale. In line with this argument, this article analyses empirically how the concept of circular economy is conceived in the institutional spheres of "industry", "government" and "university". Innovation systems are constantly being reconstructed through knowledge production and communication, which is reflected in how concepts develop in the different spheres. By applying natural language processing tools to key contributions from each of the three spheres (the "Triple Helix"), it is shown that, although institutional backgrounds do contribute to differing conceptualizations of circular economy, there is a substantial but limited conceptual consensus space, which, according to the Triple Helix, should open new opportunities for innovations. The consensus space shared across the three spheres focuses on materials and products and sees circular economy as a way to create new resources, businesses and products from waste. The industry sphere highlights business opportunities on global scale, which are also evident in the government sphere. The government sphere connects circular economy to waste-related innovation policies targeted at industrial renewal, economic growth, investments and jobs. The university sphere, in turn, focuses on production and environmental issues, waste and knowledge, and is rather distinct from the two other spheres. The importance of the differing conceptions of circular economy is based on the logic of Triple Helix systems. Accordingly, sufficient consensus between the Triple Helix spheres can advance the application of the concept of circular economy beyond the individual spheres to achieve systemic changes.
  • Aalto, Iiro (Helsingin yliopisto, 2020)
    Slack is an instant messaging platform intended for the internal communications of companies and other organizations. For organizations that use Slack extensively it may provide an interesting source of insight, but as such the data is difficult to analyze. Topic modeling, primarily latent Dirichlet allocation (LDA), is commonly used to summarize textual data in a meaningful way. Instant messages tend to be very short, which causes problems for conventional topic modeling methods such as LDA. The data sparsity problem can be tackled with data expansion and data combination techniques. For instant messages, data combination is particularly attractive as the messages are not independent of each other, but form implicit, and sometimes expicit, threads as the participants reply to each other. Most of the threads in the Slack data are not explicit, but must be ’untangled’ from the message stream if they are to be used as a basis for a data combination scheme. In this thesis we study the possibility of detecting implicit threads from a slack message stream and leveraging the threads as a data combination scheme in topic modeling. The threads are detected using a hierarchical clustering algorithm which uses word mover’s distance, latent semantic analysis, and metadata to compute the distances between messages. The clusters are then concatenated and used as the input for LDA. It is shown that on a dataset gathered from the Gofore Oyj Slack workspace, the cluster-based model improves on the message-based model, but falls short of being practical.
  • Ylä-Anttila, Tuukka Salu Santeri (2018)
    ‘Post-truth politics’, particularly as manifested in ‘fake news’ spread by countermedia, is claimed to be endemic to contemporary populism. I argue that the relationship between knowledge and populism needs a more nuanced analysis. Many have noted that populism valorises ‘common sense’ over expertise. But another populist strategy is counterknowledge, proposing politically charged alternative knowledge authorities in the stead of established ones. I analyse countermedia in Finland, where they have played a part in the rise of right-wing populism, using a combination of computational and interpretive methods. In my data, right-wing populists advocate counterknowledge; they profess belief in truth achievable by inquiry, not by mainstream experts but alternative ones. This is a different knowledge orientation from the valorisation of ‘common sense’, and there is reason to believe it is somewhat specific to contemporary right-wing anti-immigration populism. Populism’s epistemologies are multifaceted but often absolutist, as is populism’s relationship to power and democracy.
  • Pöyhtäri, Reeta; Nelimarkka, Matti; Nikunen, Kaarina; Ojala, Markus; Pantti, Mervi; Pääkkönen, Juho (2021)
    In this article, we analyse how the debate on the ‘refugee crisis’ has been constructed in Finnish news media and social media by using big data analytics. The study applies big data with the aim of exploring the dynamics between the mainstream news media and social media and the ways in which these dynamics shape and strategically amplify different understandings of the refugee crisis. The research highlights over-emphasis of crime and threat-oriented themes on refugee issues in social media, as well as illuminates the distinct role of social media platforms in shaping debates through user practices of hyperlink sharing and networked framing. Together these findings suggest that the hybrid media environment provides a possible arena for polarization of the refugee debate that could also be used for political ends.