Publications

Home /
Publications

Project Publications:

I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames

Author(s): Katharina Prasse, Isaac Bravo, Stefanie Walter, and Margret Keuper
Date Published: Jan 3, 2025

Abstract:
Visual framing analysis is a key method in social sciences for determining common themes and concepts in a given discourse. To reduce manual effort, image clustering can significantly speed up the annotation process. In this work, we phrase the clustering task as a Minimum Cost Multicut Problem [MP]. Solutions to the MP have been shown to provide clusterings that maximize the posterior probability, solely from provided local, pairwise probabilities of two images belonging to the same cluster. We discuss the efficacy of numerous embedding spaces to detect visual frames and show its superiority over other clustering methods. To this end, we employ the climate change dataset \textit{ClimateTV} which contains images commonly used for visual frame analysis. For broad visual frames, DINOv2 is a suitable embedding space, while ConvNeXt V2 returns a larger number of clusters which contain fine-grain differences, i.e. speech and protest. Our insights into embedding space differences in combination with the optimal clustering - by definition - advances automated visual frame detection.

Citation: Prasse, K. et al. (2025) I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames. WACV.
Download the paper and the code.

Towards Understanding Climate Change Perceptions: A Social Media Dataset

Author(s): Katharina Prasse, Steffen Jung, Isaac Bravo, Stefanie Walter, and Margret Keuper
Date Published: December 16, 2023

Abstract:
Climate perceptions shared on social media are an invaluable barometer of public attention. By directing research towards this topic, we can eventually improve the effectiveness of climate change communication, increase public engagement, and enhance climate change education. We propose two real-world image datasets to promote impactful research both in the Computer Vision community and beyond. Firstly, ClimateTV, a dataset containing over 700,000 climate change-related images posted on Twitter and labelled on basis of the image hashtags. Secondly, ClimateCT, a Twitter dataset containing images with five-dimensional annotations in super-categories (i) Animals, (ii) Climate action, (iii) Consequences, (iv) Setting, and (v) Type. These challenging classification datasets contain classes which are designed according to their relevance in the context of climate change. The challenging nature of the datasets is given by varying class diversities (e.g. polar bear vs. land mammal) and foci (e.g. arctic vs. snowy residential area). The analyses of our datasets using CLIP embeddings and query optimization (CoCoOp) further showcase the challenging nature of ClimateTV and ClimateCT.

Citation: Prasse, K. et al. (2023) Towards Understanding Climate Change Perceptions: A Social Media Dataset. https://www.climatechange.ai/papers/neurips2023/3
Download the paper and the data.

Climate Imagery in the Media Landscape: A Systematic Literature Review, Challenges, and Future Research

Author(s): Isaac Bravo, Stefanie Walter, Katharina Prasse and Margret Keuper
Date Published: On review - Annals of the International Communication Association.

Abstract:
Visualisations play a key role in conveying the complexities of climate change to raise awareness and encourage informed action. This paper presents a combination of systematic and scoping literature review (2005 – 2023) that employs content analysis to analyse current research on climate change visualisations of traditional and digital media landscapes. Findings show that most existing research concentrates on traditional media to the detriment of social media, with a predominance of studies focused on Western countries. Framing theory emerges as the predominant theoretical framework, especially in qualitative studies. By analysing and comparing a large corpus of scientific studies, we aim to elucidate the predominant topics, methodologies, gaps, and further strive to outline key challenges and implications for future research directions.

Conference Presentations:

I Spy With My Little Eye: A Minimum Cost Multicut Investigation of Dataset Frames.

Conference Name: Winter Conference on Applications of Computer Vision: Applications Track
Location: Tucson (AZ), USA
Author(s): Katharina Prasse, Isaac Bravo, Stefanie Walter & Margret Keuper
Date Presentation: Feb 28 - March 4, 2024

More information about the Conference, see here.

Computational Analysis of Manipulated Visual Content in Climate Change Discourse on Twitter.

Conference Name: 6th Annual COMPTEXT Conference 2024
Location: Amsterdam, Netherlands
Author(s): Katharina Prasse, Isaac Bravo, Stefanie Walter & Margret Keuper
Date Presentation: 2-4 May, 2024

More information about the Conference, see here.

Detecting Manipulated Visuals: A Computational Approach in the Climate Change Discourse.

Conference Name: Annual Conference of the “Science Communication” Division (DGPuK)
Location: Zurich, Switzerland
Author(s): Katharina Prasse, Isaac Bravo, Stefanie Walter & Margret Keuper
Date Presentation: June 6-7, 2024

More information about the Conference, see here.

Computational Analysis of Manipulated Visual Content in Climate Change Discourse on Twitter.

Towards Understanding Climate Change Perceptions: A Social Media Dataset.

Workshop Name: Tackling Climate Change with Machine Learning
Location: New Orleans, USA
Author(s): Katharina Prasse, Steffen Jung, Isaac Bravo, Stefanie Walter & Margret Keuper
Date Presentation: 16 December, 2023

More information about the Workshop, see here.

Analysing the Role of Social Media in Shaping Public Opinion on Climate Change: A Comparative Study Across Regions Using Automated Image and Text Analysis.

Conference Name: WAPOR 76th Annual Conference
Location: Salzburg, Austria
Author(s): Isaac Bravo, Katharina Prasse, Stefanie Walter & Margret Keuper
Date Presentation: 28th-29th September, 2023

More information about the Conference, see here.

Analysing the effects of visual framing on social media in shaping people’s emotional engagement on climate change.

Workshop Name: Emotions in European Climate Politics workshop
Location: Amsterdam, Netherlands
Author(s): Isaac Bravo, Katharina Prasse, Stefanie Walter & Margret Keuper
Date Presentation: 28-29 September, 2023

More information about the Workshop, see here.