Argument technology

This article possibly contains original research. Please improve it by verifying the claims made and adding inline citations. Statements consisting only of original research should be removed. (January 2019) (Learn how and when to remove this message)

Argument technology is a sub-field of collective intelligence and artificial intelligence that focuses on applying computational techniques to the creation, identification, analysis, navigation, evaluation and visualisation of arguments and debates.

In the 1980s and 1990s, philosophical theories of arguments in general, and argumentation theory in particular, were leveraged to handle key computational challenges, such as modeling non-monotonic and defeasible reasoning and designing robust coordination protocols for multi-agent systems.^[1] At the same time, mechanisms for computing semantics of Argumentation frameworks were introduced as a way of providing a calculus of opposition for computing what it is reasonable to believe in the context of conflicting arguments.^[2]

With these foundations in place, the area was kick-started by a workshop held in the Scottish Highlands in 2000, the result of which was a book coauthored by philosophers of argument, rhetoricians, legal scholars and AI researchers.^[3] Since then, the area has been supported by various dedicated events such as the International Workshop on Computational Models of Natural Argument (CMNA)^[4] which has run annually since 2001; the International Workshop on Argument in Multi Agent Systems (ArgMAS) annually since 2004; the Workshop on Argument Mining,^[5] annually since 2014, and the Conference on Computational Models of Argument (COMMA),^[6] biennially since 2006. Since 2010, the field has also had its own journal, Argument & Computation, which was published by Taylor & Francis until 2016^[7] and since then by IOS Press.^[8]

One of the challenges that argument technology faced was a lack of standardisation in the representation and underlying conception of argument in machine readable terms. Many different software tools for manual argument analysis, in particular, developed idiosyncratic and ad hoc ways of representing arguments which reflected differing underlying ways of conceiving of argumentative structure.^[9] This lack of standardisation also meant that there was no interchange between tools or between research projects, and little re-use of data resources that were often expensive to create. To tackle this problem, the Argument Interchange Format^[10] set out to establish a common standard that captured the minimal common features of argumentation which could then be extended in different settings.

Since about 2018, argument technology has been growing rapidly, with, for example, IBM's Grand Challenge, Project Debater, results for which were published in Nature in March 2021;^[11] German research funder, DFG's nationwide research programme on Robust Argumentation Machines, RATIO,^[12] begun in 2019; and UK nationwide deployment of The Evidence Toolkit by the BBC in 2019.^[13] A 2021 video narrated by Stephen Fry provides a summary of the societal motivations for work in argument technology.^[14]

Argument technology has applications in a variety of domains, including education, healthcare, policy making, political science, intelligence analysis and risk management and has a variety of sub-fields, methodologies and technologies.^[15]