Argumentation Mining in User-Generated Web Discourse

By Ivan Habernal, Iryna Gurevych. International Conference on Computational Logic, 2016

309 citations recorded by the source corpus.

The goal of argumentation mining, an evolving research field in computational linguistics, is to design methods capable of analyzing people’s argumentation. In this article, we go beyond the state of the art in several ways. (i) We deal with actual Web data and take up the challenges given by the variety of registers, multiple domains, and unrestricted noisy user-generated Web discourse. (ii) We bridge the gap between normative argumentation theories and argumentation phenomena encountered in actual data by adapting an argumentation model tested in an extensive annotation study. (iii) We create a new gold standard corpus (90k tokens in 340 documents) and experiment with several machine learning methods to identify argument components. We offer the data, source codes, and annotation guidelines to the community under free licenses. Our findings show that argumentation mining in user-generated Web discourse is a feasible but challenging task.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/834d68b9befcc6c68415b460b33435a1822799fb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Parsing Argumentation Structures in Persuasive Essays (2016, background): “el (Cabrio and Villata 2014; Boltužic´ and Šnajder 4 Stab and Gurevych Parsing Argumentation Structures 2014), different types of argument components (Mochales-Palau and Ieven 2009; Kwon et al. 2007; Habernal and Gurevych 2016), and argumentation structures over several documents (Aharoni et al. 201”
The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants (2017, background): “…for stance detection of Mohammad et al. (2016)); 2,026 arguments with 4,235 annotated reasons, which is six times larger than the 340 documents of Habernal and Gurevych (2017)); and 4,235 summarized reason gists — we are not aware of any existing hand-crafted dataset for abstractive argument…”
Let’s Make Your Request More Persuasive: Modeling Persuasive Strategies via Semi-Supervised Neural Nets on Crowdfunding Platforms (2019, background): “Most work has either identiﬁed the arguments in news articles (Sar-dianos et al., 2015) or user-generated web content (Habernal and Gurevych, 2017; Musi et al., 2018), or classiﬁed argument components (Zhang and Litman, 2015) into claims and premises, supporting and opposing claims, or backings,…”