Solidarity is a crucial concept to understand social relations in societies.In this paper, we explore fine-grained solidarity frames to study solidarity towards women and migrants in German parliamentary debates between 1867 and 2022.Using 2,864 manually annotated text snippets (with a cost exceeding 18k Euro), we evaluate large language models (LLMs) like Llama 3, GPT-3.5, and GPT-4.We find that GPT-4 outperforms other LLMs, approaching human annotation quality.Using GPT-4, we automatically annotate more than 18k further instances (with a cost of around 500 Euro) across 155 years and find that solidarity with migrants outweighs anti-solidarity but that frequencies and solidarity types shift over time.Most importantly, group-based notions of (anti-)solidarity fade in favor of compassionate solidarity, focusing on the vulnerability of migrant groups, and exchange-based anti-solidarity, focusing on the lack of (economic) contribution.Our study highlights the interplay of historical events, socio-economic needs, and political ideologies in shaping migration discourse and social cohesion.We also show that powerful LLMs, if carefully prompted, can be costeffective alternatives to human annotation for hard social scientific tasks.

We approach aspect-based argument mining as a supervised machine learning task to classify arguments into semantically coherent groups referring to the same defined aspect categories. As an exemplary use case, we introduce the Argument Aspect Corpus - Nuclear Energy that separates arguments about the topic of nuclear energy into nine major aspects. Since the collection of training data for further aspects and topics is costly, we investigate the potential for current transformer-based few-shot learning approaches to accurately classify argument aspects. The best approach is applied to a British newspaper corpus covering the debate on nuclear energy over the past 21 years. Our evaluation shows that a stable prediction of shares of argument aspects in this debate is feasible with 50 to 100 training samples per aspect. Moreover, we see signals for a clear shift in the public discourse in favor of nuclear energy in recent years. This revelation of changing patterns of pro and contra arguments related to certain aspects over time demonstrates the potential of supervised argument aspect detection for tracking issue-specific media discourses.

Protest events provide information about social and political conflicts, the state of social cohesion and democratic conflict management, as well as the state of civil society in general. Social scientists are therefore interested in the systematic observation of protest events. With this paper, we release the first German language resource of protest event related article excerpts published in local news outlets. We use this dataset to train and evaluate transformer-based text classifiers to automatically detect relevant newspaper articles. Our best approach reaches a binary F1-score of 93.3 %, which is a promising result for our goal to support political science research. However, in a second experiment, we show that our model does not generalize equally well when applied to data from time periods and localities other than our training sample. To make protest event detection more robust, we test two ways of alternative preprocessing. First, we find that letting the classifier concentrate on sentences around protest keywords improves the F1-score for out-of-sample data up to +4 percentage points. Second, against our initial intuition, masking of named entities during preprocessing does not improve the generalization in terms of F1-scores. However, it leads to a significantly improved recall of the models.

To ease the difficulty of argument stance classification, the task of same side stance classification (S3C) has been proposed.In contrast to actual stance classification, which requires a substantial amount of domain knowledge to identify whether an argument is in favor or against a certain issue, it is argued that, for S3C, only argument similarity within stances needs to be learned to successfully solve the task.We evaluate several transformer-based approaches on the dataset of the recent S3C shared task, followed by an in-depth evaluation and error analysis of our model and the task's hypothesis.We show that, although we achieve state-of-the-art results, our model fails to generalize both within as well as across topics and domains when adjusting the sampling strategy of the training and test set to a more adversarial scenario.Our evaluation shows that current state-of-the-art approaches cannot determine same side stance by considering only domain-independent linguistic similarity features, but appear to require domain knowledge and semantic inference, too.

De-identification is the task of detecting protected health information (PHI) in medical text.It is a critical step in sanitizing electronic health records (EHRs) to be shared for research.Automatic de-identification classifiers can significantly speed up the sanitization process.However, obtaining a large and diverse dataset to train such a classifier that works well across many types of medical text poses a challenge as privacy laws prohibit the sharing of raw medical records.We introduce a method to create privacy-preserving shareable representations of medical text (i.e. they contain no PHI) that does not require expensive manual pseudonymization.These representations can be shared between organizations to create unified datasets for training de-identification models.Our representation allows training a simple LSTM-CRF de-identification model to an F 1 score of 97.4%, which is comparable to a strong baseline that exposes private information in its representation.A robust, widely available de-identification classifier based on our representation could potentially enable studies for which de-identification would otherwise be too costly.

Abstract Social media are an emerging new paradigm in interdisciplinary research in crisis informatics. They bring many opportunities as well as challenges to all fields of application and research involved in the project of using social media content for an improved disaster management. Using the Central European flooding 2013 as our case study, we optimize and apply methods from the field ofnatural language processingand unsupervised machine learning to investigate the thematic and temporal structure of German social media communication. By means of topic model analysis, we will investigate which kind of content was shared on social media during the event. On this basis, we will, furthermore, investigate the development of topics over time and apply temporal clustering techniques to automatically identify different characteristic phases of communication. From the results, we, first, want to reveal properties of social media content and show what potential social media have for improving disaster management in Germany. Second, we will be concerned with the methodological issue of finding and adapting natural language processing methods that are suitable for analysing social media data in order to obtain information relevant for disaster management. With respect to the first, application-oriented focal point, our study reveals high potential of social media content in the factual, organizational and psychological dimension of the disaster and during all stages of the disaster management life cycle. Interestingly, there appear to be systematic differences in thematic profile between the different platforms Facebook and Twitter and between different stages of the event. In context of our methodological investigation, we claim that if topic model analysis is combined with appropriate optimization techniques, it shows high applicability for thematic and temporal social media analysis in disaster management.