Editing Argumentation theory (section)

== Artificial intelligence ==
{{See also|Argument technology|Argument mapping|Argumentation framework}}
[[File:Intelligent assistant for argumentative support and arguments inquiry.png|thumb|Structured debates from platforms like [[Kialo]] could be used for "artificial deliberative agents" (ADAs) or computational reasoning.<ref name="10.1145/3469595.3469615">{{cite book |last1=Anastasiou |first1=Lucas |last2=De Liddo |first2=Anna |title=Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems |chapter=Making Sense of Online Discussions: Can Automated Reports help? |date=8 May 2021 |pages=1–7 |doi=10.1145/3411763.3451815 |publisher=Association for Computing Machinery|isbn=9781450380959 |s2cid=233987842 }}</ref><ref name="Betz">{{cite journal |last1=Betz |first1=Gregor |title=Natural-Language Multi-Agent Simulations of Argumentative Opinion Dynamics |journal=Journal of Artificial Societies and Social Simulation |pages=2 |doi=10.18564/jasss.4725 |date=2022|volume=25 |arxiv=2104.06737 |s2cid=233231231 }}</ref>]]
[[File:Basic design of artificial deliberative agents (ADAs) for argumentation.png|thumb|Example of an ADA contributing missing information to a debate via crawled Kialo data and selected based [[natural language processing|on the prior conversation]] and crawled [[Kialo#collective determination of argument weights|argument weight ratings]]<ref name="Betz"/>]]
Efforts have been made within the field of [[artificial intelligence]] to perform and analyze argumentation with computers.  Argumentation has been used to provide a proof-theoretic [[semantics]] for [[non-monotonic logic]], starting with the influential work of Dung (1995). Computational argumentation systems have found particular application in domains where formal logic and classical [[decision theory]] are unable to capture the richness of reasoning, domains such as law and medicine. In ''Elements of Argumentation'', Philippe Besnard and Anthony Hunter show how classical logic-based techniques can be used to capture key elements of practical argumentation.<ref>{{cite book |last1=Besnard |first1=Philippe |last2=Hunter |first2=Anthony |date=2008 |title=Elements of Argumentation |location=Cambridge, MA |publisher=[[MIT Press]] |isbn=9780262026437 |oclc=163605008 |doi=10.7551/mitpress/9780262026437.001.0001}} Reviewed in: {{cite journal|last1=Lundström|first1=Jenny Eriksson|title=Book Reviews: Elements of Argumentation|journal=Studia Logica|date=11 September 2009|volume=93|issue=1|pages=97–103|doi=10.1007/s11225-009-9204-3|s2cid=3214194}}</ref>

Within computer science, the ArgMAS workshop series (Argumentation in Multi-Agent Systems), the CMNA workshop series,<ref>{{cite web |title=Computational Models of Natural Argument |url=https://cmna.csc.liv.ac.uk/ |website=cmna.csc.liv.ac.uk}}</ref> and the COMMA Conference,<ref>{{cite web |title=Computational Models of Argument |url=https://intranet.csc.liv.ac.uk/~comma/ |website=intranet.csc.liv.ac.uk}}</ref> are regular annual events attracting participants from every continent. The journal ''Argument & Computation''<ref>{{cite web |title=Argument & Computation |url=https://www.iospress.com/catalog/journals/argument-computation |website=www.iospress.com|date=August 2023 }}</ref> is dedicated to exploring the intersection between argumentation and computer science. ArgMining is a workshop series dedicated specifically to the related [[argument mining]] task.<ref>{{cite web|url=https://research.ibm.com/haifa/Workshops/argmining18/|title=5th Workshop on Argument Mining|date=2011-05-17|website=www.research.ibm.com}}</ref>

Data from the collaborative structured online argumentation platform [[Kialo]] has been used to train and to evaluate [[natural language processing]] AI systems such as, most commonly, [[BERT (language model)|BERT]] and its variants.{{refn|name=NLPapplic|<ref name="10.1145/3485447.3512144">{{cite book |last1=Agarwal |first1=Vibhor |last2=Joglekar |first2=Sagar |last3=Young |first3=Anthony P. |last4=Sastry |first4=Nishanth |title=Proceedings of the ACM Web Conference 2022 |chapter=GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates |date=25 April 2022 |pages=2729–2737 |doi=10.1145/3485447.3512144|arxiv=2202.08175 |isbn=9781450390965 |s2cid=246867079 }}</ref><ref>{{cite book |last1=Prakken |first1=H. |last2=Bistarelli |first2=S. |last3=Santini |first3=F. |title=Computational Models of Argument: Proceedings of COMMA 2020 |date=25 September 2020 |publisher=IOS Press |isbn=978-1-64368-107-8 |url=https://books.google.com/books?id=I6EGEAAAQBAJ |language=en}}</ref><ref name="conclusion">{{cite arXiv |title=Conclusion-based Counter-Argument Generation |eprint=2301.09911 |last1=Alshomary |first1=Milad |last2=Wachsmuth |first2=Henning |year=2023 |class=cs.CL }}</ref><ref>{{cite journal |last1=Thorburn |first1=Luke |last2=Kruger |first2=Ariel |title=Optimizing Language Models for Argumentative Reasoning |date=2022 |url=https://ceur-ws.org/Vol-3208/paper3.pdf}}</ref><ref name="Revise"/><ref name="Durmus">{{cite book |last1=Durmus |first1=Esin |last2=Ladhak |first2=Faisal |last3=Cardie |first3=Claire |title=Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics |chapter=Determining Relative Argument Specificity and Stance for Complex Argumentative Structures |pages=4630–4641 |doi=10.18653/v1/P19-1456 |date=2019|arxiv=1906.11313 |s2cid=195699602 }}</ref><ref name="Bolton">{{cite arXiv |title=High Quality Real-Time Structured Debate Generation |eprint=2012.00209 |last1=Bolton |first1=Eric |last2=Calderwood |first2=Alex |last3=Christensen |first3=Niles |last4=Kafrouni |first4=Jerome |last5=Drori |first5=Iddo |year=2020 |class=cs.CL }}</ref><ref>{{cite journal |last1=Jo |first1=Yohan |last2=Bang |first2=Seojin |last3=Reed |first3=Chris |last4=Hovy |first4=Eduard |title=Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes |journal=Transactions of the Association for Computational Linguistics |date=2 August 2021 |volume=9 |pages=721–739 |doi=10.1162/tacl_a_00394|s2cid=234742133 |arxiv=2105.07571 }}</ref><ref name="impactrating">{{cite book |last1=Durmus |first1=Esin |last2=Ladhak |first2=Faisal |last3=Cardie |first3=Claire |title=Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |chapter=The Role of Pragmatic and Discourse Context in Determining Argument Impact |pages=5667–5677 |doi=10.18653/v1/D19-1568 |date=2019|arxiv=2004.03034 |s2cid=202768765 }}</ref><ref name="Khatib">{{cite book |last1=Al Khatib |first1=Khalid |last2=Trautner |first2=Lukas |last3=Wachsmuth |first3=Henning |last4=Hou |first4=Yufang |last5=Stein |first5=Benno |chapter=Employing Argumentation Knowledge Graphs for Neural Argument Generation |title=Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) |date=August 2021 |pages=4744–4754 |doi=10.18653/v1/2021.acl-long.366 |chapter-url=https://aclanthology.org/2021.acl-long.366.pdf |publisher=Association for Computational Linguistics|s2cid=236460348 }}</ref>}} This includes argument extraction, conclusion generation,<ref name="conclusion"/>{{additional citation needed|date=June 2023}} argument form quality assessment,<ref name="Skitalinskaya">{{cite arXiv |title=Learning From Revisions: Quality Assessment of Claims in Argumentation at Scale |eprint=2101.10250 |last1=Skitalinskaya |first1=Gabriella |last2=Klaff |first2=Jonas |last3=Wachsmuth |first3=Henning |year=2021 |class=cs.CL }} The study investigates revisions of the same argument for machine learning of general style quality assessment.</ref> machine argumentative debate generation or participation,<ref name="Bolton"/><ref name="impactrating"/><ref name="Khatib"/> surfacing most relevant previously overlooked viewpoints or arguments,<ref name="Bolton"/><ref name="impactrating"/> argumentative writing support<ref name="Revise">{{cite arXiv |title=To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support |eprint=2305.16799 |last1=Skitalinskaya |first1=Gabriella |last2=Wachsmuth |first2=Henning |year=2023 |class=cs.CL }}</ref> (including sentence attackability scores),<ref name="Detecting"/> automatic real-time evaluation of how truthful or convincing a sentence is (similar to [[fact-checking]]),<ref name="Detecting">{{cite arXiv |title=Detecting Attackable Sentences in Arguments |eprint=2010.02660 |last1=Jo |first1=Yohan |last2=Bang |first2=Seojin |last3=Manzoor |first3=Emaad |last4=Hovy |first4=Eduard |last5=Reed |first5=Chris |year=2020 |class=cs.CL }}</ref> [[Fine-tuning (machine learning)|language model fine tuning]]<ref>{{cite book |last1=Fanton |first1=Margherita |last2=Bonaldi |first2=Helena |last3=Tekiroglu |first3=Serra Sinem |last4=Guerini |first4=Marco |title=Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) |chapter=Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech |pages=3226–3240 |doi=10.18653/v1/2021.acl-long.250 |date=2021|arxiv=2107.08720 |s2cid=236087808 }}</ref><ref name="Khatib"/> (including for [[chatbot]]s),<ref>{{cite journal |last1=Björklin |first1=Hampus |last2=Abrahamsson |first2=Tim |last3=Widenfalk |first3=Oscar |title=A retrieval-based chatbot's opinion on the trolley problem |date=2021 |url=https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1571401}}</ref><ref>{{cite arXiv |title=Opening up Minds with Argumentative Dialogues |eprint=2301.06400 |last1=Farag |first1=Youmna |last2=Brand |first2=Charlotte O. |last3=Amidei |first3=Jacopo |last4=Piwek |first4=Paul |last5=Stafford |first5=Tom |last6=Stoyanchev |first6=Svetlana |last7=Vlachos |first7=Andreas |year=2023 |class=cs.CL }}</ref> argument impact prediction, argument classification and polarity prediction.<ref name="graphbased">{{cite journal |last1=Agarwal |first1=Vibhor |last2=P. Young |first2=Anthony |last3=Joglekar |first3=Sagar |last4=Sastry |first4=Nishanth |title=A Graph-Based Context-Aware Model to Understand Online Conversations |journal=ACM Transactions on the Web |year=2024 |volume=18 |pages=1–27 |doi=10.1145/3624579 |arxiv=2211.09207 }}</ref><ref>{{cite journal |title=Towards an Argument Mining Pipeline Transforming Texts to Argument Graphs |doi=10.3233/FAIA200510 |arxiv=2006.04562 |last1=Lenz |first1=Mirko |last2=Sahitaj |first2=Premtim |last3=Kallenberg |first3=Sean |last4=Coors |first4=Christopher |last5=Dumani |first5=Lorik |last6=Schenkel |first6=Ralf |last7=Bergmann |first7=Ralph |year=2020 |pages=263–270 |publisher=IOS Press |s2cid=219531343 }}</ref>