Argumentation scheme mining is the task of automatically identifying reasoning mechanisms behind argument inferences. These mechanisms provide insights into underlying argument structures and guide the assessment of natural language arguments. Research on argumentation scheme mining, however, has always been limited by the scarcity of large enough publicly available corpora containing scheme annotations. In this paper, we present the first state-of-the-art results for mining argumentation schemes in natural language dialogue. For this purpose, we create QT-SCHEMES, a new corpus of 441 arguments annotated with 24 argumentation schemes. Using this corpus, we leverage the capabilities of LLMs and Transformer-based models, pre-training them on a large corpus containing textbook-like argumentation schemes and validating their applicability in real-world scenarios.

Accurate forecasting of future events is critical across domains such as finance, policymaking, and intelligence analysis. In this work we investigate the role of argumentative reasoning in successful forecasting. Drawing on theories of argumentation, we perform a fine-grained annotation of forecasts and their supporting rationales from a major forecasting competition, identifying argumentative structures and discourse moves. We derive a variety of structural and textual features from the resulting argument graphs, such as argumentative balance, support, and conflict. We perform a correlation analysis to examine the relationship of individual features to forecasting success, and apply a Graph Neural Network (GNN) to learn from these structures, enriching the node representations with text embeddings. Our results show that balanced argumentative coverage has a statistically significant correlation with forecasting success, and that models incorporating argument graphs and text embeddings outperform baselines that use surface text alone when predicting forecasting success. To our knowledge, this is the first study to systematically link fine-grained argumentative structure and graph-based reasoning to forecasting accuracy, offering novel insights into strategies that support more accurate predictions of future events. By identifying key argumentative features that correlate with forecasting success, this work provides valuable guidance for developing tools and strategies to improve forecasting accuracy, with applications across multiple decision-making domains.

In computational argument mining, the final constructed argument graph is usually the center of attention, with researchers analyzing its structure and developing methods to extract valuable insights from it. In this paper, we argue that analyzing only the final argument graph is not enough. We demonstrate that the same argument graphs do not imply the same argument construction styles (ways of populating them), which are an important abstract argumentation concept. Therefore, both final structure and the construction style should be considered when analyzing arguments. To address the analysis of argument construction styles, we present the DRACS: Diachronic Representation of Argument Construction Styles framework to capture argument construction style features and enable their analysis alongside the graph structures. We evaluate our methodology on three distinct datasets of pre-defined similar and differing construction styles: the AIF-labeled corpora UNSC and US2016, as well as a custom corpus of synthetic tree-based argument graphs. We apply our method to highlight similarities and differences of argument construction styles on US2016 datasets. Our findings suggest that even if the final argument graphs display a high degree of similarity, their construction styles could differ significantly.

It is known from large-scale crowd experimentation that some people are innately better at analysing complex situations and making justified predictions – the so-called ‘superforecasters’. Surprisingly, however, there has to date been no work exploring the role played by the reasoning in those justifications. Bag-of-words analyses might tell us something, but the real value lies in understanding what features of reasoning and argumentation lead to better forecasts – both in providing an objective measure for argument quality, and even more importantly, in providing guidance on how to improve forecasting performance. The work presented here covers the creation of a unique dataset of such prediction rationales, the structure of which naturally lends itself to partially automated annotation which in turn is used as the basis for subsequent manual enhancement that provides a uniquely fine-grained and close characterisation of the structure of argumentation, with potential impact on forecasting domains from intelligence analysis to investment decision-making.

Dialogue protocols define how a dialogue may proceed and the moves its participants can make within it. The scope of this work covers protocol switching, and addresses the current gap in the area of illicit protocol switches in dialogue. Over the course of a dialogue the participants’ goals and strategies may change in response to the other participants within the dialogue. Enabling agents to switch between protocols gives them the flexibility to address these changes and make use of them. This paper introduces protocol switching using Dialogue as a Service (DaaS), a platform for building multi-agent dialogue systems. DaaS can be used to create a wide range of multi-agent dialogue systems due to its few restrictions and inherent flexibility, which is illustrated through the use of two examples from the literature. Protocol switches can be both licit and illicit; however, current research has only focused on implementing licit protocol switches. An approach to facilitating and managing illicit protocol switches is demonstrated herein.

Generating and evaluating hypotheses about past, present, and future events is core to argumentation in many domains, such as forensic investigations, medical diagnostics, and scientific research. In this paper, we explore the role of hypothesis-making in argumentative dialogue. To do so, we introduce an annotated dataset of 502 hypotheses in the existing RIP corpus of collaborative problem-solving in murder mystery games, creating the RIP1 corpus. Propositions marked as hypotheses in RIP1 correlate systematically with argument structure (previously annotated according to Inference Anchoring Theory). We explore the interaction between arguments and hypotheses, showing hypotheses are often conclusions of arguments and differences between how hypotheses and assertions are treated in dialogue. Based on this quantitative analysis, we conduct preliminary computational experiments establishing a baseline for the automatic mining of hypotheses. Experimentation with a Support Vector Machine and a fine-tuned RoBERTa model shows initial performance on text span classification with an F1 score of 80.0, outperforming random and majority baselines, and providing a target for future improvement.

Following the establishment in 2006 of a representational standard for the computational handling of structures of argumentation, the Argument Interchange Format, it became possible to develop a vision for the coherent integration of multifarious services, components and tools that create, consume, navigate, analyse, evaluate and manipulate arguments and debates. This vision was the Argument Web with theoretical foundations laid by Rahwan et al. (2007), and practical engineering work described by Bex et al. (2013). Over the intervening period, the key challenge has been to demonstrate the practical and societal value of the Argument Web by taking its tools and applications to larger audiences. This paper lays out three approaches by which the Argument Web has been scaled up in this way, each in partnership with the BBC, and each with different kinds of evaluation and impact. Transitioning these technologies to large user groups paves the way for broader-scale uptake of the Argument Web and heralds the translation from lab to real-world application for a substantial research community working in argument technology.

In this paper, we present Polemicist 2, a dialogical interface for exploring complex debates from the BBC Radio 4 programme The Moral Maze. Polemicist allows the user to interact with software agents representing the participants in the original programme. The software enables the user to explore the topic as they wish, asking questions to dive deeper on the areas that interest them most.

Skeptic is a web service aimed at automatically providing pointers for the critical assessment of a persuasive text. That is, with a natural language text as input, the web service returns a ranked list of questions designed to help readers reason-check fake news and other contentious texts. Internally, Skeptic maps argumentative features of the text to methods for critical assessment, such as the critical questions of argument schemes, ways of evaluating different types of propositions, and signs of possible biased reasoning. The argumentative features are retrieved by utilising extant techniques for argument mining and classification.

Argument mining is the automatic identification and extraction of the structure of inference and reasoning expressed as arguments presented in natural language. Understanding argumentative structure makes it possible to determine not only what positions people are adopting, but also why they hold the opinions they do, providing valuable insights in domains as diverse as financial market prediction and public relations. This survey explores the techniques that establish the foundations for argument mining, provides a review of recent advances in argument mining techniques, and discusses the challenges faced in automatically extracting a deeper understanding of reasoning expressed in language in general.

In this paper, we present Test Your Argument, part of a suite of argument technology piloted in conjunction with BBC programming. Test Your Argument offers users the opportunity to interact with real arguments taken from the BBC Radio 4 programme Moral Maze. Users are guided through different aspects of strengthening and critiquing an argument as well as considering both sides of the issue under discussion. Since December 2017, Test Your Argument has had over 10,000 visitors.

In this paper, we present an in-depth comparative analysis of two classifications of argument schemes: Walton's typology and Wagemans' Periodic Table of Arguments. We describe annotation guidelines for each classification and apply these to a corpus of arguments from the 2016 US presidential debates. In so doing, we achieve substantial inter-annotator agreement, and produce what, to the best of our knowledge, are the two largest and most reliably annotated corpora of argument schemes in dialogical argumentation publicly available. In describing the creation and comparison of these corpora, we discuss the strengths of each, with an eye towards both computational modelling and argument mining.

The simulation of mathematical reasoning has been a driving force throughout the history of Artificial Intelligence research. However, despite significant successes in computer mathematics, computers are not widely used by mathematicians apart from their quotidian applications. An oft-cited reason for this is that current computational systems cannot do mathematics in the way that humans do. We draw on two areas in which Automated Theorem Proving (ATP) is currently unlike human mathematics: firstly in a focus on soundness, rather than understandability of proof, and secondly in social aspects. Employing techniques and tools from argumentation to build a framework for mixed-initiative collaboration, we develop three complementary arcs. In the first arc – our theoretical model – we interpret the informal logic of mathematical discovery proposed by Lakatos, a philosopher of mathematics, through the lens of dialogue game theory and in particular as a dialogue game ranging over structures of argumentation. In our second arc – our abstraction level – we develop structured arguments, from which we induce abstract argumentation systems and compute the argumentation semantics to provide labelings of the acceptability status of each argument. The output from this stage corresponds to a final, or currently accepted proof artefact, which can be viewed alongside its historical development. Finally, in the third arc – our computational model – we show how each of these formal steps is available in implementation. In an appendix, we demonstrate our approach with a formal, implemented example of real-world mathematical collaboration. We conclude the paper with reflections on our mixed-initiative collaborative approach.

Governments around the world are increasingly utilising online platforms and social media to engage with, and ascertain the opinions of, their citizens. Whilst policy makers could potentially benefit from such enormous feedback from society, they first face the challenge of making sense out of the large volumes of data produced. In this article, we show how the analysis of argumentative and dialogical structures allows for the principled identification of those issues that are central, controversial, or popular in an online corpus of debates. Although areas such as controversy mining work towards identifying issues that are a source of disagreement, by looking at the deeper argumentative structure, we show that a much richer understanding can be obtained. We provide results from using a pipeline of argument-mining techniques on the debate corpus, showing that the accuracy obtained is sufficient to automatically identify those issues that are key to the discussion, attracting proportionately more support than others, and those that are divisive, attracting proportionately more conflicting viewpoints.

Debating technologies, a newly emerging strand of research into computational technologies to support human debating, offer a powerful way of providing naturalistic, dialogue-based interaction with complex information spaces. The full potential of debating technologies for dialogical argument can, however, only be realized once key technical and engineering challenges are overcome, namely data structure, data availability, and interoperability between components. Our aim in this article is to show that the Argument Web, a vision for integrated, reusable, semantically rich resources connecting views, opinions, arguments, and debates online, offers a solution to these challenges. Through the use of a running example taken from the domain of citizen dialogue, we demonstrate for the first time that different Argument Web components focusing on sensemaking, engagement, and analytics can work in concert as a suite of debating technologies for rich, complex, dialogical argument.

We propose a dialogue game for mediation and its formalization in DGDL. This dialectical system is available as software through Arvina for automatic execution. This work expands the literature in dialectical systems, in particular those for more than two players, and shows the practical impact on mediation activity through the opportunity offered to mediators once implemented.

Rapid growth in the area of argument mining has resulted in an ever increasing volume of analysed argument data. Being able to store information about arguments people make in favour or against different opinions, decisions and actions is a highly valuable resource, yet extremely challenging for sense-making. How, for example, can an analyst quickly check whether in a corpus of citizen dialogue people tend to rather agree or disagree with new policies proposed by the department of transportation; how can she get an insight into the interactions typical of this specific dialogical context; how can the general public easily see which presidential candidate is currently winning the debate by being able to successfully defend his arguments? In this paper, we propose Argument Analytics – a suite of techniques which provide interpretation of, and insight into, large-scale argument data for both specialist and general audiences.

Argumentation schemes are patterns of human reasoning which have been detailed extensively in philosophy and psychology. In this paper we demonstrate that the structure of such schemes can provide rich information to the task of automatically identify complex argumentative structures in natural language text. By training a range of classifiers to identify the individual proposition types which occur in these schemes, it is possible not only to determine where a scheme is being used, but also the roles played by its component parts. Furthermore, this task can be performed on segmented natural language, with no prior knowledge of the text's argumentative structure.

In this paper, we present the Dialogue Game Execution Platform (DGEP), which is able to process and execute any dialogue game specified in a general description language and build arguments and dialogue histories in the language of the AIF ontology. Thus, DGEP allows us to generalise techniques for generation and investigation of dialogues and, through a set of web services, connect a wide variety of multi-agent systems and human-computer interfaces for dialogue.

This paper introduces OVA+, an on-line interface for the analysis of arguments. It is the result of an attempt to provide a tool relying on the Argument Interchange Format theory and Inference Anchoring Theory schemes.

This paper introduces AIFdb Corpora, an addition to AIFdb for collecting and presenting sets of AIF argument maps. AIFdb Corpora allows any user to create a corpus and share the contents.

We present a dialogue game representation of Lakatos's theory of justification and discovery in mathematics and describe our implementation of the game. As well as demonstrating a new domain for dialogue games, this could provide the basis for systems which can be used to aid mathematicians in their work.

In this paper, we present a software tool for ‘ArguBlogging’, which allows users to construct debate and discussions across blogs, linking existing and new online resources to form distributed, structured conversations. Arguments and counterarguments can be posed by giving opinions on one’s own blog and replying to other bloggers’ posts. The resulting argument structure is connected to the Argument Web, in which argumentative structures are made semantically explicit and machine-processable. We discuss the ArguBlogging tool and the underlying infrastructure and ontology of the Argument Web.

This paper gives a historical overview of the development of the U.K. marine energy sector from its academic beginnings in the early 1970s. It includes discussion on government support policies and where the sector might develop up to and beyond the end of this decade. The paper also presents two very different projects: the European Marine Energy Centre in Orkney, U.K., and the forthcoming All Waters Current and Wave Test Facility in Edinburgh, U.K., as examples of capital investment in the sector.

We have implemented a translator that translates Carneades Argument Graphs as specified in the LKIF files of the Carneades editor to a database specification of the Argument Interchange Format and vice versa. In this paper the algorithms for this translation are presented.

In this paper, we present Arvina, an online discussion tool supporting mixed initiative argumentation. Arvina allows stored arguments in the Argument Web to be introduced by software agents which human participants can then interact with.

This paper introduces AIFdb, a database solution for the Argument Web. AIFdb offers an array of web service interfaces allowing a wide range of software to interact with the same argument data.

In this paper, we present ArguBlogging, a simple tool that allows blog users to directly respond to text on a web page, publishing the response to their blog while simultaneously capturing the argumentative structure in the Argument Web via the Argument Interchange Format.

A marine X-band radar has been deployed at a coastal location overlooking a region of extreme tidal currents used for the testing of tidal stream energy turbines. Near-surface tidal currents are known to reach 3.8m/s in water depths of the order of 50m. Preliminary results from the analysis of radar data collected at this site will be presented with particular reference to the currents determined using an inversion of the wave spectrum. Comparisons will be made with current profile data collected using an Acoustic Doppler Current Profiler (ADCP) deployed within the field of view of the radar.

Software tools for working with argument generally exist as large systems that wrap their entire feature set in the application as a whole. This approach, while perfectly valid, can result in users having to use small parts of multiple systems to carry out a specific task. In this paper, we present a series of web services, that each encapsulate small pieces of functionality for working with argument. We then demonstrate two example systems built by connecting these services in the form of a UNIX-style pipeline.

Abstract It is proved that for a variety of groups in which the relatively free groups are solvable, the relatively free groups of distinct finite rank are not elementarily equivalent.