Stance Detection with a Multi-Target Adversarial Attention Network

Abstract

Stance detection aims to assign a stance label (in favor or against) to a post towards a specific target. In the literature, there are many studies focusing on this topic, and most of them treat stance detection as a supervised learning task. Therefore, a new classifier needs to be built from scratch on a well-prepared set of ground-truth data whenever predictions are needed for an unseen target. However, it is difficult to annotate the stance of a post, since a stance is a subjective attitude towards a target. Hence, it is necessary to learn the information from unlabeled data or other target data to help stance detection with a certain target. In this study, we propose a multi-target stance detection framework to integrate multi-target data together for stance detection. Since topic and sentiment are two important factors to identify the stance of a post in multi-target data, we propose an adversarial attention network to integrate multi-target data by detecting and connecting topic and sentiment information. In particular, the adversarial network is utilized to determine the topic and the sentiment of each post to collect some target-invariant information for stance detection. In addition, the attention mechanism is utilized to connect posts with a similar topic or sentiment to acquire some key information for stance detection. The experimental results not only demonstrate the effectiveness of the proposed model, but also indicate the importance of the topic and the sentiment information for stance detection using multi-target data.

Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-training

“…Stance and Sentiment Sentiment Analysis has a long history of association with stance (Somasundaran, Ruppenhofer, and Wiebe 2007;Somasundaran and Wiebe 2010). Sentiment is often annotated in parallel to stance (Mohammad et al 2016;Hercig, Krejzl, and Král 2018) and has been used extensively as a feature (Ebrahimi, Dou, and Lowd 2016;Sobhani, Mohammad, and Kiritchenko 2016;Sun et al 2018) or as an auxiliary task (Li and Caragea 2019;Sun et al 2019) for improving stance detection. Missing from these studies, however, is leveraging sentiment annotations to generate noisy stance examples, which we explore here: for English and in a multilingual setting.…”

STEM: Unsupervised STructural EMbedding for Stance Detection

“…Modal verbs, opinion and sentiment lexicons were used in early works by (Somasundaran and Wiebe 2010;Murakami and Raymond 2010;Yin et al 2012;Wang and Cardie 2014;Bar-Haim et al 2017). Recent text-based works use graphical models (Joseph et al 2017), CRFs (Hasan and Ng 2013) and various neural architectures (Hiray and Duppada 2017; Sun et al 2018;Chen et al 2018;Kobbe, Hulpus , , and Stuckenschmidt 2020), among others. These methods are language, and often domain, dependent.…”

A novel approach to stance detection in social media tweets by fusing ranked lists and sentiments

“…For instance, [9] looked for tweets (using the SemEval-2016 task 6 dataset, or just SemEval-2016 dataset in this Section) that contained the following words and phrases: "atheism", "climate change" etc. On the other hand, [19] examined thousands of documents that contained the terms "marijuana", "Obama", etc as part of detecting stance in H&N14 dataset [20]. The IberEval-2017 dataset tackles a single target, the "independence of Catalonia", where the collected tweets were in Spanish or Catalan.…”

“…Next, we examine researches that used deep learning techniques. Sun et al [19] presented a hierarchical attention network (HAN) to weight the importance of different linguistic information and learn the mutual attention between the linguistic information and the document. The authors tested their system on the SemEval-2016 dataset and reported the performance of an F -score of 61%.…”