DFKI-LT - Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs

Nils Rethmeier, Marc Hübner, Leonhard Hennig
Learning Comment Controversy Prediction in Web Discussions Using Incidentally Supervised Multi-Task CNNs
3 Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Pages 316-321, Brussels, Belgium, Association for Computational Linguistics, 10/2018,
http://aclweb.org/anthology/W18-6246

 
Comments on web news contain controversies that manifest as inter-group agreementconflicts. Tracking such rapidly evolving controversy could ease conflict resolution or journalist-user interaction. However, this presupposes controversy online-prediction that scales to diverse domains using incidental supervision signals instead of manual labeling. To more deeply interpret commentcontroversy model decisions we frame prediction as binary classification and evaluate baselines and multi-task CNNs that use an auxiliary news-genre-encoder. Finally, we use ablation and interpretability methods to determine the impacts of topic, discourse and sentiment indicators, contextual vs. global word influence, as well as genre-keywords vs. per-genrecontroversy keywords – to find that the models learn plausible controversy features using only incidentally supervised signals.
 
Files: BibTeX, W18-6246, W18-6246.pdf