STANCY: Stance Classification Based on Consistency Cues

Abstract

Controversial claims are abundant in online media and discussion forums.A better understanding of such claims requires analyzing them from different perspectives. Stance classification is a necessary step for inferring these perspectives in terms of supporting or opposing the claim. In this work, we present a neural network model for stance classification leveraging BERT representations and augmenting them with a novel consistency constraint. Experiments on the Perspectrum dataset, consisting of claims and users' perspectives from various debate websites, demonstrate the effectiveness of our approach over state-of-the-art baselines.

SERN: Stance Extraction and Reasoning Network for Fake News Detection

“…The goal of our stance extractor is to model the stance of the user reply R i to the post P automatically, where R i is the i th reply of post P . Motivated by recent stance classification works [17,18], we firstly construct post-reply pairs, and concatenate each pair into a single sentence by using a special classification token [CLS] and two separator token [SEP], as shown in Fig 2 . Then We feed each concatenated post-reply pair into BERT 1 , and the final hidden state representation corresponding to the [CLS] token is used as the stance representation X P |Ri ∈ R H , where H = 768. Specifically, the BERT model we use here consists of 12 layers and 12 heads, which is pre-trained on lower-cased English text, that is,…”

Stance Prediction for Contemporary Issues: Data and Experiments

“…49 out of its 947 claims are from procon (Chen et al, 2019). Claims and perspectives are short sentences and have been used for stance detection in (Popat et al, 2019).…”

Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media

“…49 out of its 947 claims are from procon . Claims and perspectives are short sentences and have been used for stance detection in (Popat et al, 2019).…”

“…There are also some neural network approaches that leverage lexical features (Riedel et al, 2017;Hanselowski et al, 2018). A consistency constraint is proposed to jointly model the topic and opinion using BERT architecture (Popat et al, 2019). It trains the whole massive network for label prediction.…”

“…• BERT CONS is a BERT base model that considers two different inputs using a perspective and its respective claim (Popat et al, 2019). The first input is similar to BERT sentence model's, [CLS] claim [SEP] perspective…”