Discourse Parsing of Contentious, Non-Convergent Online Discussions
This work provides a new method for analyzing polarized online discussions, which is important for researchers and developers interested in understanding and moderating online discourse, though it is an incremental improvement on existing parsing methods.
This paper addresses the challenge of parsing contentious online discussions, which existing frameworks struggle with due to their non-convergent nature. The authors propose a new theoretical and computational framework, achieving an average F-Score of 0.61 with separate models for 31 labels and 0.526 with a single model.
Online discourse is often perceived as polarized and unproductive. While some conversational discourse parsing frameworks are available, they do not naturally lend themselves to the analysis of contentious and polarizing discussions. Inspired by the Bakhtinian theory of Dialogism, we propose a novel theoretical and computational framework, better suited for non-convergent discussions. We redefine the measure of a successful discussion, and develop a novel discourse annotation schema which reflects a hierarchy of discursive strategies. We consider an array of classification models -- from Logistic Regression to BERT. We also consider various feature types and representations, e.g., LIWC categories, standard embeddings, conversational sequences, and non-conversational discourse markers learnt separately. Given the 31 labels in the tagset, an average F-Score of 0.61 is achieved if we allow a different model for each tag, and 0.526 with a single model. The promising results achieved in annotating discussions according to the proposed schema paves the way for a number of downstream tasks and applications such as early detection of discussion trajectories, active moderation of open discussions, and teacher-assistive bots. Finally, we share the first labeled dataset of contentious non-convergent online discussions.