Modeling Appropriate Language in Argumentation
38618Authors
nan
Abstract
AbstractOnline discussion moderators must make ad-hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offensive language and the resulting tools cover only one aspect among many involved in such decisions. The question of what is considered appropriate in a controversial discussion has not yet been systematically addressed. In this paper, we operationalize appropriate language in argumentation for the first time. In particular, we model appropriateness through the absence of flaws, grounded in research on argument quality assessment, especially in aspects from rhetoric. From these, we derive a new taxonomy of 14 dimensions that determine inappropriate language in online discussions. Building on three argument quality corpora, we then create a corpus of 2191 arguments annotated for the 14 dimensions. Empirical analyses support that the taxonomy covers the concept of appropriateness comprehensively, showing several plausible correlations with argument quality dimensions. Moreover, results of baseline approaches to assessing appropriateness suggest that all dimensions can be modeled computationally on the corpus.
Keywords
Full Content
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics Volume 1: Long Papers, pages 4344–4363 July 9-14, 2023 ©2023 Association for Computational Linguistics Modeling Appropriate Language in Argumentation Timon Ziegenbein Leibniz University Hannover t.ziegenbein@ai.uni-hannover.de Shahbaz Syed Leipzig University shahbaz.syed@uni-leipzig.de Felix Lange Paderborn University flange@mail.uni-paderborn.de Martin Potthast Leipzig University and ScaDS.AI martin.potthast@uni-leipzig.de Henning Wachsmuth Leibniz University Hannover h.wachsmuth@ai.uni-hannover.de Abstract Online discussion moderators must make ad- hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Ex- isting research on offensive language and the resulting tools cover only one aspect among many involved in such decisions. The question of what is considered appropriate in a controver- sial discussion has not yet been systematically addressed. In this paper, we operationalize ap- propriate language in argumentation for the first time. In particular, we model appropriateness through the absence of flaws, grounded in re- search on argument quality assessment, espe- cially in aspects from rhetoric. From these, we derive a new taxonomy of 14 dimensions that determine inappropriate language in online dis- cussions. Building on three argument quality corpora, we then create a corpus of 2191 argu- ments annotated for the 14 dimensions. Em- pirical analyses support that the taxonomy cov- ers the concept of appropriateness comprehen- sively, showing several plausible correlations with argument quality dimensions. Moreover, results of baseline approaches to assessing ap- propriateness suggest that all dimensions can be modeled computationally on the corpus. 1 Introduction People have varying degrees of sensitivity to con- troversial issues and may be triggered by different emotional responses dependent on the issue and the opponents’ arguments (Walton, 2010). This often makes it hard to maintain a constructive discussion. In competitive debates, a moderator ensures that participants argue appropriately. Debating culture, dating back to the 18th century, demands appropri- ate behavior, such as staying on topic and avoiding overly emotional language (Andrew, 1996). Ac- “There is scientific evidence that shows having a mother and a father is the healthiest way for a child to progress physically and mentally. So a lousy father is better than none (that is of course assuming that he is not abusive in any way). Also, people change. Who says that he will be lousy forever. There are family therapy sessions you can attend to help.” Appropriate Argument “There is scientific evidence that shows having a mother and a father is the healthiest way for a child to progress physically and mentally. So a lousy father is better than none (that is of course assuming that he is not abusive in any way). Also, people change. Who says that he will be lousy forever. There are family therapy sessions you can attend to help.” [Issue: Is it better to have a lousy father or to be fatherless?] Inappropriate Argument [Issue: Pro choice vs pro life] “for everyone who is talking about RAPE in this subject let me ask you one thing!!!! if you got in a huge fight with someone and ended up …
Content truncated to 500 words
Labeled Text
AbstractOnline discussion moderators must make ad-hoc decisions about whether the contributions of discussion participants are appropriate or should be removed to maintain civility. Existing research on offensive language and the resulting tools cover only one aspect among many involved in such decisions. The question of what is considered appropriate in a controversial discussion has not yet been systematically addressed. In this paper, we operationalize appropriate language in argumentation for the first time. In particular, we model appropriateness through the absence of flaws, grounded in research on argument quality assessment, especially in aspects from rhetoric. From these, we derive a new taxonomy of 14 dimensions that determine inappropriate language in online discussions. Building on three argument quality corpora, we then create a corpus of 2191 arguments annotated for the 14 dimensions. Empirical analyses support that the taxonomy covers the concept of appropriateness comprehensively, showing several plausible correlations with argument quality dimensions. Moreover, results of baseline approaches to assessing appropriateness suggest that all dimensions can be modeled computationally on the corpus.
Publication Details
- Paper ID:
- 38618
- Year:
- 2023
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan