In online discussions, users often back up their stance with arguments. Their argu-ments are often vague, implicit, and poorly worded, yet they provide valuable insights into reasons underpinning users ’ opinions. In this paper, we make a first step towards argument-based opinion mining from on-line discussions and introduce a new task of argument recognition. We match user-created comments to a set of predefined topic-based arguments, which can be either attacked or supported in the comment. We present a manually-annotated corpus for ar-gument recognition in online discussions. We describe a supervised model based on comment-argument similarity and entail-ment features. Depending on problem for-mulation, model performance ranges from 70.5 % to 81.8 % F1-score, and decreases only marginally when applied to an unseen topic. 1
No takes yet. Share an insight, caveat, or question.
Boltužić et al. (2014) studied this question.