What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process

Abstract

In our world with full of uncertainty, debates and argumentation contribute to the progress of science and society. Despite of the increasing attention to characterize human arguments, most progress made so far focus on the debate outcome, largely ignoring the dynamic patterns in argumentation processes. This paper presents a study that automatically analyzes the key factors in argument persuasiveness, beyond simply predicting who will persuade whom. Specifically, we propose a novel neural model that is able to dynamically track the changes of latent topics and discourse in argumentative conversations, allowing the investigation of their roles in influencing the outcomes of persuasion. Extensive experiments have been conducted on argumentative conversations on both social media and supreme court. The results show that our model outperforms state-of-the-art models in identifying persuasive arguments via explicitly exploring dynamic factors of topic and discourse. We further analyze the effects of topics and discourse on persuasiveness, and find that they are both useful -topics provide concrete evidence while superior discourse styles may bias participants, especially in social media arguments. In addition, we draw some findings from our empirical results, which will help people better engage in future persuasive conversations.

ResPer: Computationally Modelling Resisting Strategies in Persuasive Conversations

“…The closest semblance to our work in NLP literature ties in with argumentation, be it essays (Carlile et al, 2018), debates (Cano-Basave andHe, 2016), or discussions on social media platforms (Al-Khatib et al, 2018;Zeng et al, 2020). Such works have revolved mostly on analysing argumentative strategies and their effect on others.…”

Exploring Discourse Structures for Argument Impact Classification

“…In addition to the features mentioned above, the role of pragmatic and discourse contexts has shown to be crucial by not yet fully explored. Zeng et al (2020) examined how the contexts and the dynamic progress of argumentative conversations influence the comparative persuasiveness of an argumentation process. created a new dataset based on argument claims and impact votes from a debate platform kialo.com, and experiments showed that incorporating contexts is useful to classify the argument impact.…”

Leveraging Topic Relatedness for Argument Persuasion

“…Bosc et al (2016) proposes a dataset of Social Media data with coarse topic labels extracted from the hashtags (e.g., #Ap-pleWatch). Zeng et al (2020) designed a model to encode the latent topics of argumentative conversations. Unlike the previous work, our work studies the effect of argument topic for structured debates explicitly for predicting persuasion.…”