Stance Detection with Bidirectional Conditional Encoding

By Isabelle Augenstein, Tim Rocktaschel, Andreas Vlachos, Kalina Bontcheva. Conference on Empirical Methods in Natural Language Processing, 2016

451 citations recorded by the source corpus.

Stance detection is the task of classifying the attitude expressed in a text towards a target such as Hillary Clinton to be "positive", negative" or "neutral". Previous work has assumed that either the target is mentioned in the text or that training data for every target is given. This paper considers the more challenging version of this task, where targets are not always mentioned and no training data is available for the test targets. We experiment with conditional LSTM encoding, which builds a representation of the tweet that is dependent on the target, and demonstrate that it outperforms encoding the tweet and the target independently. Performance is improved further when the conditional model is augmented with bidirectional encoding. We evaluate our approach on the SemEval 2016 Task 6 Twitter Stance Detection corpus achieving performance second best only to a system trained on semi-automatically labelled tweets for the test target. When such weak supervision is added, our approach achieves state-of-the-art results.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8e7d063c681557c94382ff3da6415d3720fe11a7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

emoji2vec: Learning Emoji Representations from their Description (2016, background): “Many current NLP systems applied to social media rely on representation learning and word embeddings (Tang et al., 2014; Dong et al., 2014; Dhingra et al., 2016; Augenstein et al., 2016).”
Stance Detection on Social Media: State of the Art and Trends (2020, methodology): “Most of the previous studies focused on inferring the stance for a set of predefined targets [Mohammad et al. 2016; Kareem et al. 2019; Augenstein et al. 2016a; Liu et al. 2016; Dias and Becker 2016; Igarashi et al. 2016].”
Zero-Shot Stance Detection: A Dataset and Model Using Generalized Topic Representations (2020, methodology): “• BiCond : a model for cross-target stance that uses bidirectional encoding, whereby the topic is encoded using a BiLSTM as h t and the text is then encoded using a second BiLSTM conditioned on h t (Augenstein et al., 2016).”
MultiFC: A Real-World Multi-Domain Dataset for Evidence-Based Fact Checking of Claims (2019, background): “to fact checking, are stance detection for claims (Ferreira and Vlachos, 2016; Pomerleau and Rao, 2017; Augenstein et al., 2016a; Kochkina et al., 2017; Augenstein et al., 2016b; Zubiaga et al., 2018; Riedel et al., 2017), satire detection (Rubin et al.”
X -stance: A Multilingual Multi-Target Dataset for Stance Detection (2020, background): “Augenstein et al. (2016) propose a conditional encoding approach to encode both the target and the tweet as sequences.”
Deep learning for sentiment analysis: A survey (2018, background): “Stance Detection: Augenstein et al.(147) proposed a bidirectional LSTMs with a conditional encoding mechanism for stance detection in political twitter data.”
Author’s Sentiment Prediction (2020, background): “In stance detection the models are looking for favorability towards a given target of interest which may not be mentioned or targeted in the text (Mohammad et al., 2016; Augenstein et al., 2016).”
How would Stance Detection Techniques Evolve after the Launch of ChatGPT? (2022, methodology): “Convolutional neural network (CNN) and long short-term memory (LSTM) models are most commonly used conventional DNN models (Augenstein et al., 2016; Du et al., 2017); the attention-based methods mainly utilize target-speciﬁc information as the attention query, and deploy an attention mechanism for…”