Towards Debate Automation: a Recurrent Model for Predicting Debate Winners

Potash, Peter; Rumshisky, Anna

doi:10.18653/v1/d17-1261

Cited by 22 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There is a rich body of prior work on classifying the outcome of a conversation after it has concluded, or classifying conversational events after they happened. Many examples exist, but some more closely related to our present work include identifying the winner of a debate (Zhang et al, 2016;Potash and Rumshisky, 2017;Wang et al, 2017), identifying successful negotiations (Curhan and Pentland, 2007;Cadilhac et al, 2013), as well as detecting whether deception (Girlea et al, 2016;Pérez-Rosas et al, 2016;Levitan et al, 2018) or disagreement (Galley et al, 2004;Abbott et al, 2011;Allen et al, 2014;Wang and Cardie, 2014;Rosenthal and McKeown, 2015) has occurred.…”

Section: Further Related Workmentioning

confidence: 88%

Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop

Chang¹,

Danescu-Niculescu-Mizil²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

Online discussions often derail into toxic exchanges between participants. Recent efforts mostly focused on detecting antisocial behavior after the fact, by analyzing single comments in isolation. To provide more timely notice to human moderators, a system needs to preemptively detect that a conversation is heading towards derailment before it actually turns toxic. This means modeling derailment as an emerging property of a conversation rather than as an isolated utterance-level event.Forecasting emerging conversational properties, however, poses several inherent modeling challenges. First, since conversations are dynamic, a forecasting model needs to capture the flow of the discussion, rather than properties of individual comments. Second, real conversations have an unknown horizon: they can end or derail at any time; thus a practical forecasting model needs to assess the risk in an online fashion, as the conversation develops. In this work we introduce a conversational forecasting model that learns an unsupervised representation of conversational dynamics and exploits it to predict future derailment as the conversation develops. By applying this model to two new diverse datasets of online conversations with labels for antisocial events, we show that it outperforms state-of-the-art systems at forecasting derailment.

show abstract

Section: Further Related Workmentioning

confidence: 88%

Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop

Chang¹,

Danescu-Niculescu-Mizil²

2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

View full text Add to dashboard Cite

show abstract

“…In contrast, our data set contains both same stance pairs, as well as cross stance pairs (i.e., one is supporting and the other is contesting the topic). Thus it is aligned with the above mentioned task, but in addition, with the task of choosing which side of the debate was more convincing (Potash and Rumshisky, 2017).…”

Section: Introductionmentioning

confidence: 82%

Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network

Gleize¹,

Shnarch²,

Choshen³

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Machines capable of responding and interacting with humans in helpful ways have become ubiquitous. We now expect them to discuss with us the more delicate questions in our world, and they should do so armed with effective arguments. But what makes an argument more persuasive? What will convince you?In this paper, we present a new data set, IBM-EviConv, of pairs of evidence labeled for convincingness, designed to be more challenging than existing alternatives. We also propose a Siamese neural network architecture shown to outperform several baselines on both a prior convincingness data set and our own. Finally, we provide insights into our experimental results and the various kinds of argumentative value our method is capable of detecting. 1 For more details and a video of the debate: https. 2017. Argumentation quality assessment: Theory vs. practice. In ACL 2017. Lisa Weltzer-Ward, Beate Baltes, and Laura Knight Lynn. 2009. Assessing quality of critical thought in online discussion. Campus-Wide Information Systems, 26(3):168-177.

show abstract

“…User factors are explored in previous papers Cardie, 2019a, 2018;Longpre et al, 2019), demonstrating the importance of characteristics and beliefs of the audience. Furthermore, Potash and Rumshisky (2017) proposed a recurrent neural network architecture with attention and annotated audience favorability to predict the winner of the debate. Villata et al (2018) and Benlamine et al (2017) studied the correlation of the engagement index in brain hemispheres with the persuasion strategies.…”

Section: Related Workmentioning

confidence: 99%

Exploring the Role of Argument Structure in Online Debate Persuasion

Durmus

Cardie

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Online debate forums provide users a platform to express their opinions on controversial topics while being exposed to opinions from diverse set of viewpoints. Existing work in Natural Language Processing (NLP) has shown that linguistic features extracted from the debate text and features encoding the characteristics of the audience are both critical in persuasion studies. In this paper, we aim to further investigate the role of discourse structure of the arguments from online debates in their persuasiveness. In particular, we use the factor graph model to obtain features for the argument structure of debates from an online debating platform and incorporate these features to an LSTM-based model to predict the debater that makes the most convincing arguments. We find that incorporating argument structure features play an essential role in achieving the better predictive performance in assessing the persuasiveness of the arguments in online debates.

show abstract

Towards Debate Automation: a Recurrent Model for Predicting Debate Winners

Cited by 22 publications

References 27 publications

Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop

Trouble on the Horizon: Forecasting the Derailment of Online Conversations as they Develop

Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network

Exploring the Role of Argument Structure in Online Debate Persuasion

Contact Info

Product

Resources

About