Marie Lisa Kogler

Raven Adam, Marie Kogler. Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025). 2025.

This study introduces Bidirectional Topic Matching (BTM), a novel method for cross-corpus topic modeling that quantifies thematic overlap and divergence between corpora. BTM is a flexible framework that can incorporate various topic modeling approaches, including BERTopic, Top2Vec, and Latent Dirichlet Allocation (LDA). BTM employs a dual-model approach, training separate topic models for each corpus and applying them reciprocally to enable comprehensive cross-corpus comparisons. This methodology facilitates the identification of shared themes and unique topics, providing nuanced insights into thematic relationships. Validation against cosine similarity-based methods demonstrates the robustness of BTM, with strong agreement metrics and distinct advantages in handling outlier topics. A case study on climate news articles showcases BTM's utility, revealing significant thematic overlaps and distinctions between corpora focused on climate change and climate action. BTM's flexibility and precision make it a valuable tool for diverse applications, from political discourse analysis to interdisciplinary studies. By integrating shared and unique topic analyses, BTM offers a comprehensive framework for exploring thematic relationships, with potential extensions to multilingual and dynamic datasets. This work highlights BTM's methodological contributions and its capacity to advance discourse analysis across various domains.

Contagions refer to the spread or transmission of diseases, behaviors, beliefs, or emotions. While some contagions easily propagate throughout entire populations, others seem to be more constrained and propagate only within specific parts of the population. This arises not just because of different transmission rates but because of qualitative differences in the mechanisms with which contagions propagate throughout a network. Diseases typically propagate through single connections, while behaviors and beliefs often necessitate multiple connections for further propagation, termed complex contagions. In this paper, we propose a graph reduction method to reduce a network to include only connections immediately relevant to the propagation of a complex contagion. Through repeated application, we obtain structures that remain stable under the reduction, allowing us to define and measure for any given network, (i) strongly contagious components, (ii) weakly contagious components, and (iii) bridge components. Information about the size and location of these components can be used as a meaningful basis to assess and prevent the potential spread of harmful contagions as well as incentivize the spread of beneficial contagions.