Infusing Knowledge from Wikipedia to Enhance Stance Detection

Abstract

Stance detection infers a text author's attitude towards a target. This is challenging when the model lacks background knowledge about the target. Here, we show how background knowledge from Wikipedia can help enhance the performance on stance detection. We introduce Wikipedia Stance Detection BERT (WS-BERT) that infuses the knowledge into stance encoding. Extensive results on three benchmark datasets covering social media discussions and online debates indicate that our model significantly outperforms the state-of-the-art methods on target-specific stance detection, cross-target stance detection, and zero/few-shot stance detection. 1

Distantly Supervised Explainable Stance Detection via Chain-of-Thought Supervision

“…The incorporation of background knowledge to enhance stance detection capabilities has garnered significant interest, representing a promising strategy to amplify its efficacy [29]. He et al [13] introduced an approach that integrates target-related background knowledge, such as encyclopedic information from Wikipedia, and devised a fine-tuning methodology to augment the model's learning proficiency. In a similar vein, Liu et al [10] constructed a knowledge graph representing background knowledge and employed graph neural network techniques to develop an advanced stance prediction model.…”

“…Recently, some research has addressed the issue of data sparsity by integrating external knowledge, thus enhancing both the performance and the interpretability of stance detection processes. For example, He et al [13] augmented text classifiers by supplementing them with relevant Wikipedia documents about the target. Diaz et al [14] constructed a stance tree using external knowledge extracted from a knowledge base and utilized it as evidence to enhance stance prediction and detection precision.…”

Leveraging Chain-of-Thought to Enhance Stance Detection with Prompt-Tuning

“…The use of background knowledge to enhance the performance of stance detection has garnered attention as an effective approach to improving performance [28]. For instance, He et al [11] introduced target-related background knowledge, such as Wikipedia knowledge, and proposed a fine-tuning learning method to improve the model's learning ability. Similarly, Luo et al [10] constructed background knowledge as a knowledge graph and utilized graph neural network methods to develop a stance predictor.…”

“…Recently, some pioneering studies have been conducted to address the sparsity problem by utilizing external knowledge to enhance the performance and interpretability of stance detection. For example, He et al [11] improved the performance of text classifiers by introducing target-related Wikipedia documents as content supplements. Diaz et al [12] constructed a stance tree by retrieving external knowledge from a knowledge base and used it as evidence to support stance prediction, thus enhancing the accuracy of stance detection.…”