Ines Rehbein

In recent years, an increasing number of studies has been published in the newly emerging text-as-data field. More and more scholars in the areas of political and social science are taking advantage of the ever increasing amount of text available (not only on the internet, but also transcriptions of parliamentary debates, newspaper texts, or party manifestos) to address a heterogeneous set of research questions. While this trend has already brought many promising results, it is not free of risks and challenges. In their seminal paper, Grimmer and Stewart (2013) not only discuss the potential of text-as-data approaches but also highlight the pitfalls that arise when applying NLP methods for the investigation of questions from political and social science. We therefore argue for a closer collaboration between scholars from the social/political sciences on the one hand, and researchers from the area of computer science, NLP and computational linguistics on the other hand, to overcome those challenges and advance the state of the art for applications in the field of computational social science. As a first step to bridge the gap between the different communities, we organised the 1st Workshop on Computational Linguistics for the Political and Social Sciences (CPSS 2021). 1 The workshop took place in September 2021 as a virtual event, co-located with the Conference on Natural Language Processing (KONVENS 2021) in Düsseldorf, Germany. To meet the diverse needs of our research fields, we not only asked for long and short paper submissions but also for non-archival abstracts, in order to allow researchers to discuss work in progress without committing to a publication. The workshop program included five long and four short paper presentations and six non-archival abstracts that have been presented as posters. The presentations covered a wide range of topics, starting from NLP tools and corpus annotation that support research in the social science (Glaser,

During the past 15 years, automatic text scaling has become one of the key tools of the Text as Data community in political science. Prominent text-scaling algorithms, however, rely on the assumption that latent positions can be captured just by leveraging the information about word frequencies in documents under study. We challenge this traditional view and present a new, semantically aware text-scaling algorithm, SemScale , which combines recent developments in the area of computational linguistics with unsupervised graph-based clustering. We conduct an extensive quantitative analysis over a collection of speeches from the European Parliament in five different languages and from two different legislative terms, and we show that a scaling approach relying on semantic document representations is often better at capturing known underlying political dimensions than the established frequency-based (i.e., symbolic) scaling method. We further validate our findings through a series of experiments focused on text preprocessing and feature selection, document representation, scaling of party manifestos, and a supervised extension of our algorithm. To catalyze further research on this new branch of text-scaling methods, we release a Python implementation of SemScale with all included datasets and evaluation procedures.

Ines Rehbein, Simone Paolo Ponzetto, Anna Adendorf, Oke Bahnsen, Lukas Stoetzer, Heiner Stuckenschmidt. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework of syntactic analysis. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this article is twofold: (1) to provide a condensed, though comprehensive, overview of such treebanks -- based on available literature -- along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The overarching goal of this article is to provide a common framework for researchers interested in developing similar resources in UD, thus promoting cross-linguistic consistency, which is a principle that has always been central to the spirit of UD.

Bich-Ngoc Do, Ines Rehbein. Proceedings of the 28th International Conference on Computational Linguistics. 2020.

Parsing learner data poses a great challenge for standard tools, since non-canonical and unusual structures may lead to wrong interpretations on the part of the taggers and parsers. It is well known that providing a statistical parser with perfect part-of-speech (POS) tags is of great benefit for parsing accuracy, and that parsing results can decrease considerably when the parser has to predict its own POS tags. Therefore one might expect that even small improvements in POS accuracy have a positive effect on parsing performance. In this paper we test this assumption and assess the impact of POS tag accuracy on constituency parsing for German learner language. We compare different strategies to manual correction of the learner text and specific POS tags, and we measure the time requirements for each strategy. We show that tagging a canonical equivalent of the non-canonical learner text substantially improves POS tag accuracy. Correcting selected POS tags can only lead to parsing results comparable to a setting where all POS tags are corrected, while reducing annotation time substantially. However, the manual corrections of the POS tags do not result in a statistically significant improvement for parsing, giving evidence for the high quality of the automatically predicted parts-of-speech for the corrected learner data.