Patterns of Argumentation Strategies across Topics

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1351–1357 Copenhagen, Denmark, September 7–11, 2017. c⃝2017 Association for Computational Linguistics Patterns of Argumentation Strategies across Topics Khalid Al-Khatib Henning Wachsmuth Matthias Hagen Benno Stein Faculty of Media, Bauhaus-Universität Weimar, Germany <firstname>.<lastname>@uni-weimar.de Abstract This paper presents an analysis of argumen- tation strategies in news editorials within and across topics. Given nearly 29,000 ar- gumentative editorials from the New York Times, we develop two machine learning models, one for determining an editorial’s topic, and one for identifying evidence types in the editorial. Based on the distri- bution and structure of the identified types, we analyze the usage patterns of argumen- tation strategies among 12 different topics. We detect several common patterns that provide insights into the manifestation of argumentation strategies. Also, our experi- ments reveal clear correlations between the topics and the detected patterns. 1 Introduction Most current research in computational argumen- tation addresses argument mining, i.e., the identi- fication of pro and con arguments in a text. Com- putational approaches that study how to deliver the arguments persuasively are still scarce — despite the importance of such studies for envisaged ap- plications that deal with the synthesis of effective argumentation, such as debating systems. Many studies have indicated that it is important to follow a specific strategy of how to deliver argu- ments in order to achieve persuasion in argumenta- tive texts, and they proposed models for possible strategies. A recent work in this direction models the argumentation strategy of a text as an author’s decision on what types of evidence to include in the text as well as on how to order them (Al-Khatib et al., 2016). This is in line with studies in com- munication theory, where many experiments have been conducted on the persuasiveness of different evidence types (Hornikx, 2005) and their combina- tions (Allen and Preiss, 1997). Based on the model of Al-Khatib et al. (2016), the paper at hand investigates the usage patterns of argumentation strategies within and across topics. The study is rooted in our hypotheses that (1) ef- fective strategies for synthesizing an argumentative text can be derived from the analysis of existing strategies that humans use in high-quality texts, and (2) the decision for preferring one strategy over an- other is affected by several text characteristics such as genre, provenance, and topic. We approach our study within three steps. Start- ing from a collection of argumentative news edito- rials, we (1) categorize the editorials into n topics, (2) identify the evidence types (statistics, testimony, anecdote) in each editorial, and (3) analyze the selection and ordering of evidence types within ed- itorials across topics. The output of these steps will be beneficial for synthesizing an effective argumen- tative text for a given topic (see Figure 1). The first two steps are carried out with supervised learning based on selected linguistic features, whereas the third step quantifies the distribution of evidence types and their flows (Wachsmuth et al., 2015). To evaluate …

Content truncated to 500 words