Argumentation Mining in User-Generated Web Discourse

Abstract

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.Comment: Cite as: Habernal, I. & Gurevych, I. (2017). Argumentation Mining in User-Generated Web Discourse. Computational Linguistics 43(1), pp. 125-17

Cross-lingual Flames Detection in News Discussions

“…Including comments opens many above-mentioned use cases. Natural language processing (NLP) technology can help to make sense out of this data, in particular, the field of argumentation mining (Habernal and Gurevych, 2017). Sentiment analysis, in its basic definition, reveals the polarity of the texts (positive, negative, neutral).…”

Using New York Times Picks to Identify Constructive Comments

“…An argumentative text is one that contains argumentation, i.e., a claim supported by evidence, and presented as a coherent whole. The extensive literature on argumentation has identified linguistics aspects that pinpoint to argumentative texts (Biber, 1988;van Eemeren et al, 2007;Moens et al, 2007;Tseronis, 2011;Habernal and Gurevych, 2017). Based on this research, we include argumentation lexical cues, such as discourse connectives and stance adverbials, in our set of features.…”

Fill the Gap! Analyzing Implicit Premises between Claims from Online Debates

“…However, if the documents are sufficiently long, argumentative structure could in principle be recovered. In a recent study on social media texts, Habernal and Gurevych (2016) showed that (a slightly modified) Toulmin's argumentation model may be suitable for short documents, such as article comments or forum posts. Using sequence labeling, they identify the claim, premise, backing, rebuttal, and refutation components, achieving a token-level F1-score of 0.25.…”