Argument mining has focused so far mainly on the identification, extraction, and formalization of arguments. An important yet unaddressedtask consists in the prediction of the argumentative behavior of stakeholders in a debate. Predicting the argumentative behavior in advance can support foreseeing issues in public policy making or help recognize potential disagreements early on and help to resolve them. In this paper, we consider the novel task of predicting the argumentative behavior of individual stakeholders. We present ARGENST, a framework that relies on a recommender-based architecture to predict the stance and the argumentative main point on a specific controversial topic for a given stakeholder, which is described in terms of a profile including properties related to demographic attributes, religious and political orientation, socio-economic background, etc. We evaluate our approach on the well-known debate.org dataset in terms of accuracy for predicting stance as well as in terms of similarity of the generated arguments to the ground truth arguments using BERTScore. As part of a case study, we show how juries of members representing different stakeholder groups and perspectives can be assembled to simulate the public opinion on a given topic.

We are presenting LODinG – Linked Open Data in the Humanities (abbreviated from Linked Open Data in den Geisteswissenschaften), a recently launched research initiative exploring the intersection of Linked Open Data (LOD) and a range of areas of work within the Humanities. We focus on effective methods of collecting, modeling, linking, releasing and analyzing machine-readable information relevant to (digital) humanities research in the form of LOD. LODinG combines the sources and methods of digital humanities, general and computational linguistics, digital lexicography, German and Romance philology, translatology, cultural and literary studies, media studies, information science and law to explore and expand the potential of the LOD paradigm for such a diverse and multidisciplinary field. The project’s primary objectives are to improve the methods of extracting, modeling and analyzing multilingual data in the LOD paradigm; to demonstrate the application of the linguistic LOD to various methods and domains within and beyond the humanities; and to develop a modular, cross-domain data model for the humanities.

In this paper, we present QualiAssistant, a free and open-source system written in Java for identification and extraction of Qualia structures from any natural language texts having many application scenarios such as argument mining or creating dictionaries. It answers the call for a Qualia bootstrapping tool with a ready-to-use system that can be gradually filled by the community with patterns in multiple languages. Qualia structures express the meaning of lexical items. They describe, e.g., of what kind the item is (formal role), what it includes (constitutive role), how it is brought about (agentive role), and what it is used for (telic role). They are also valuable for various Information Retrieval and NLP tasks. Our application requires search patterns for Qualia structures consisting of POS tag sequences as well as the dataset the user wants to search for Qualias. Samples for both are provided alongside this paper. While samples are in German, QualiAssistant can process all languages for which constituency trees can be generated and patterns are available. Our provided patterns follow a high-precision low-recall design aiming to generate automatic annotations for text mining but can be exchanged easily for other purposes. Our evaluation shows that QualiAssistant is a valuable and reliable tool for finding Qualia structures in unstructured texts.