That is your evidence?: Classifying stance in online political debate

Walker, Marilyn A.; Anand, Pranav; Abbott, Rob; Tree, Jean E. Fox; Martell, Craig; King, Joseph

doi:10.1016/j.dss.2012.05.032

Cited by 99 publications

(64 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For that reason, it makes sense to use features which have been shown to work well on other political classification problems. We therefore base our feature set on that used by Walker et al (2012b) for political debate classification. Our features are described below.…”

Section: Featuresmentioning

confidence: 99%

“…Based on other work (Fox Tree and Schrock, 1999;Fox Tree and Schrock, 2002;Groen et al, 2010;Walker et al, 2012b), we also present our classifiers with features representing the first lemmatized unigram, bigram, and trigram appearing in each comment. These may be useful in our task when, for example, a user's comment begins with or entirely consists of a restatement of the answer she chose.…”

Section: Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Vote Prediction on Comments in Social Polls

Persing¹,

Ng²

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

A poll consists of a question and a set of predefined answers from which voters can select. We present the new problem of vote prediction on comments, which involves determining which of these answers a voter selected given a comment she wrote after voting. To address this task, we exploit not only the information extracted from the comments but also extra-textual information such as user demographic information and inter-comment constraints. In an evaluation involving nearly one million comments collected from the popular SodaHead social polling website, we show that a vote prediction system that exploits only textual information can be improved significantly when extended with extra-textual information.

show abstract

Section: Featuresmentioning

confidence: 99%

Section: Featuresmentioning

confidence: 99%

Vote Prediction on Comments in Social Polls

Persing¹,

Ng²

2014

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Previous work on stance in online debates has shown that contextual information given by reply links is important for stance classification (Walker et al, 2012a), and that collective classification often outperforms methods which treat each post independently. Hasan and Ng (2013) use conditional random fields (CRFs) to encourage opposite stances between sequences of posts, and Walker et al (2012c) use MaxCut over explicitly given rebuttal links between posts to separate them into PRO and ANTI clusters.…”

Section: Online Debate Forumsmentioning

confidence: 99%

Joint Models of Disagreement and Stance in Online Debate

Sridhar

Foulds

Huang

et al. 2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

111

102

View full text Add to dashboard Cite

Online debate forums present a valuable opportunity for the understanding and modeling of dialogue. To understand these debates, a key challenge is inferring the stances of the participants, all of which are interrelated and dependent. While collectively modeling users' stances has been shown to be effective (Walker et al., 2012c;Hasan and Ng, 2013), there are many modeling decisions whose ramifications are not well understood. To investigate these choices and their effects, we introduce a scalable unified probabilistic modeling framework for stance classification models that 1) are collective, 2) reason about disagreement, and 3) can model stance at either the author level or at the post level. We comprehensively evaluate the possible modeling choices on eight topics across two online debate corpora, finding accuracy improvements of up to 11.5 percentage points over a local classifier. Our results highlight the importance of making the correct modeling choices for online dialogues, and having a unified probabilistic modeling framework that makes this possible.

show abstract

“…Stance classification has been applied to several different means of argumentation, for example congressional debates (Thomas et al, 2006;Yessenalina et al, 2010) or online discussions (Somasundaran and Wiebe, 2009;Walker et al, 2012b;Hasan and Ng, 2013 work has improved stance classification by using the conversation structure (e.g., discussion reply links) (Walker et al, 2012a;Sridhar et al, 2015) or by applying classification to groups of arguments linked by citations or agreement/disagreement (Burfoot et al, 2011;Sridhar et al, 2014). However, many features used in previous works were not available for our task.…”

Section: Related Workmentioning

confidence: 99%

Improving Claim Stance Classification with Lexical Knowledge Expansion and Context Utilization

Bar-Haim¹,

Edelstein²,

Jochim³

et al. 2017

Proceedings of the 4th Workshop on Argument Mining

View full text Add to dashboard Cite

Stance classification is a core component in on-demand argument construction pipelines. Previous work on claim stance classification relied on background knowledge such as manually-composed sentiment lexicons. We show that both accuracy and coverage can be significantly improved through automatic expansion of the initial lexicon. We also developed a set of contextual features that further improves the state-of-the-art for this task.

show abstract

That is your evidence?: Classifying stance in online political debate

Cited by 99 publications

References 12 publications

Vote Prediction on Comments in Social Polls

Vote Prediction on Comments in Social Polls

Joint Models of Disagreement and Stance in Online Debate

Improving Claim Stance Classification with Lexical Knowledge Expansion and Context Utilization

Contact Info

Product

Resources

About