Argument(ation) mining (AM) is the automated process of identification and extraction of argumentative structures in natural language. This field has seen rapid advancements, offering powerful tools to analyze and interpret complex and large discourse in diverse domains (political debates, medical reports, etc.). In this paper we introduce an AM-boosted version of BCause, a large-scale deliberation platform.The system enables the extraction and analysis of arguments from online discussions in the context of deliberative democracy, which aims to enhance the understanding and accessibility of structured argumentation in large-scale deliberation processes.

In order to overcome challenges of traditional deliberation approaches that often silo information exchange between synchronous and asynchronous modes therefore hindering effective deliberation, we present a hybrid framework combining Large Language Models (LLMs) and human-in-the-loop curation to generate argument maps from deliberation transcripts. This approach aims to enhance the efficiency and quality of the generated argument maps, promote transparency, and connect the asynchronous and synchronous deliberation modes. Finally, we outline a realistic deliberation scenario where this process can be successfully integrated.

Facilitating healthy online deliberation in terms of sensemaking and collaboration of discussion participants proves extremely challenging due to a number of known negative effects of online communication on social media platforms. We start from concerns and aspirations about the use of existing online discussion systems as distilled in previous literature, we then combine them with lessons learned on design and engineering practices from our research team, to inform the design of an easy-to-use tool (BCause.app) that enables higher quality discussions than traditional social media. We describe the design of this tool, highlighting the main interaction features that distinguish it from common social media, namely: i. the low-cost argumentation structuring of the conversations with direct replies; ii. and the distinctive use of reflective feedback rather than appreciative-only feedback. We then present the results of a controlled A/B experiment in which we show that the presence of argumentative and cognitive reflective discussion elements produces better social interaction with less polarization and promotes a more cohesive discussion than common social media-like interactions.

Deduplication is the task of identifying near and exact duplicate data items in a collection. In this paper, we present a novel method for deduplication of scholarly documents. We develop a hybrid model which uses structural similarity (locality sensitive hashing) and meaning representation (word embeddings) of document texts to determine (near) duplicates. Our collection constitutes a subset of multidisciplinary scholarly documents aggregated from research repositories. We identify several issues causing data inaccuracies in such collections and motivate the need for deduplication. In lack of existing dataset suitable for study of deduplication of scholarly documents, we create a ground truth dataset of 100K scholarly documents and conduct a series of experiments to empirically establish optimal values for the parameters of our deduplication method. Experimental evaluation shows that our method achieves a macro F1-score of 0.90. We productionise our method as a publicly accessible web API service serving deduplication of scholarly documents in real time.