Improving Claim Stance Classification with Lexical Knowledge
            Expansion and Context Utilization

Bar-Haim, Roy; Edelstein, Lilach; Jochim, Charles; Slonim, Noam

doi:10.18653/v1/w17-5104

Cited by 20 publications

(17 citation statements)

References 15 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the BBC features that showed to be highly ranked according to the feature selection process. The feature extraction process was implemented in Python, and we used spacy 5 for the sentence parsing and the POS-tagging. Our final feature set consists of 21 features, presented in Table 3 with a short description.…”

Section: Methodsmentioning

confidence: 99%

“…The majority of these studies addressed stance-taking as a binary issue, however, recent studies used a wider spectrum of stance concepts to support or deny a claim/rumour [4,5,45]. The identification of stance has also been addressed from an Information Visualisation perspective namely the uVSAT tool for visual stance analysis created by Kucher et al [23].…”

Section: Background Workmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Stance-Related Characteristics in Social Media Text

Simaki

Simakis²,

Paradis

et al. 2018

Proceedings of the 10th Hellenic Conference on Artificial Intelligence

View full text Add to dashboard Cite

In this paper, we present a study for the identification of stancerelated features in text data from social media. Based on our previous work on stance and our findings on stance patterns, we detected stance-related characteristics in a data set from Twitter and Facebook. We extracted various corpus-, quantitative-and computational-based features that proved to be significant for six stance categories (contrariety, hypotheticality, necessity, prediction, source of knowledge, and uncertainty), and we tested them in our data set. The results of a preliminary clustering method are presented and discussed as a starting point for future contributions in the field. The results of our experiments showed a strong correlation between different characteristics and stance constructions, which can lead us to a methodology for automatic stance annotation of these data.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Background Workmentioning

confidence: 99%

Detection of Stance-Related Characteristics in Social Media Text

Simaki

Simakis²,

Paradis

et al. 2018

Proceedings of the 10th Hellenic Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Another class of stance detection approaches uses the context of the post, such as its relations to other posts in the debate, the network of authors, or the author's identity (Hasan and Ng, 2013;Sridhar et al, 2014;Addawood et al, 2017;Bar-Haim et al, 2017b). By contrast, we target claim-topic pairs in isolation.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised stance detection for arguments from consequences

Kobbe¹,

Hulpuș²,

Stuckenschmidt³

2020

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

View full text Add to dashboard Cite

Social media platforms have become an essential venue for online deliberation where users discuss arguments, debate, and form opinions. In this paper, we propose an unsupervised method to detect the stance of argumentative claims with respect to a topic. Most related work focuses on topic-specific supervised models that need to be trained for every emergent debate topic. To address this limitation, we propose a topic independent approach that focuses on a frequently encountered class of arguments, specifically, on arguments from consequences. We do this by extracting the effects that claims refer to, and proposing a means for inferring if the effect is a good or bad consequence. Our experiments provide promising results that are comparable to, and in particular regards even outperform BERT. Furthermore, we publish a novel dataset of arguments relating to consequences, annotated with Amazon Mechanical Turk.

show abstract

“…Zou et al (2018) determines attention weights using lexicon labels, which lead the model to focus on the lexicon words. Bar-Haim et al (2017) proposes an idea of expanding lexicons to improve stance classifying task.…”

Section: Related Workmentioning

confidence: 99%

Lexicon Guided Attentive Neural Network Model for Argument Mining

Lin¹,

Huang

et al. 2019

Proceedings of the 6th Workshop on Argument Mining

View full text Add to dashboard Cite

Identification of argumentative components is an important stage of argument mining. Lexicon information is reported as one of the most frequently used features in the argument mining research. In this paper, we propose a methodology to integrate lexicon information into a neural network model by attention mechanism. We conduct experiments on the UKP dataset, which is collected from heterogeneous sources and contains several text types, e.g., microblog, Wikipedia, and news. We explore lexicons from various application scenarios such as sentiment analysis and emotion detection. We also compare the experimental results of leveraging different lexicons.

show abstract

Improving Claim Stance Classification with Lexical Knowledge Expansion and Context Utilization

Cited by 20 publications

References 15 publications

Detection of Stance-Related Characteristics in Social Media Text

Detection of Stance-Related Characteristics in Social Media Text

Unsupervised stance detection for arguments from consequences

Lexicon Guided Attentive Neural Network Model for Argument Mining

Contact Info

Product

Resources

About