Stance Detection of Microblog Text Based on Two-Channel CNN-GRU Fusion Network

Abstract

In recent years, stance detection has become an important topic in the field of natural language processing. In earlier work, researchers have used feature engineering for stance detection but they need to define and extract appropriate features according to the particular application. This leads to poor generalization and a complex modeling process. Other researchers have applied deep learning methods. However, the popular convolutional neural network (CNN) method has the problem of information loss and a single-size CNN filter cannot accurately extract features that have different lengths from text, and so cannot deal with the diverse nature of features. In order to address these problems, we propose a two-channel CNN-GRU fusion network. First, a convolution layer with two filters with different window sizes is used to extract local features within the topic content and text content. Then, a gated recurrent unit (GRU) network is used to extract their timing characteristics. After that, the intermediate features are spliced and input to a classifier to complete the stance detection. Our method is validated using data from NLPCC 2016. The experimental results show that ACC and average F1 score of this method are 13.1% and 15.6% better than SVM method, 6.2% and 11.6% better than CNN method, 5.6% and 3.3% better than GRU method, and 1.1% and 2.2% better compared with hybrid model proposed by Nanyu, respectively, which is used as a baseline with no increase in run-time, and achieves the same accuracy with less run-time than another baseline of a semantic attention-based model proposed by Zhou. In addition, our method allows better classification than the single channel model. Finally, we find that the operation time of a multi-channel CNN-GRU increases gradually with increasing number of channels, but the classification accuracy does not improve, so a two-channel CNN-GRU is the most appropriate choice.

A systematic review of machine learning techniques for stance detection and its applications

“…The political or government domain is the dominant topic area targeted by most stance detection approaches. These approaches are applied to different political events or actors, such as Hilary Clinton (all studies that considered the SE16-T6 dataset), the Turkish election [ 94 , 95 ], the war in Syria [ 75 , 83 , 87 , 93 ], Catalan independence [ 55 , 74 ], the US presidential candidates [ 103 , 140 – 142 ], gun control and rights [ 80 , 96 ], and the BREXIT referendum [ 35 , 90 ]. In terms of the social domain, all studies that considered the SE16-T6 dataset evaluated their models on two social topics: atheism and the feminist movement.…”

Addressing Event-Driven Concept Drift in Twitter Stream: A Stance Detection Application

“…The rather poor performance figures are also observed with regard to other datasets, e.g. for the Chinese microblog stance detection task (NLPCC 2016), with a best case accuracy of 60.6% and average F-score of 62.2 [20].…”

Online Monitoring of Stance from Tweets: The case of Green Pass in Italy

“…Moreover, it is worth to observe that no specific benchmark datasets are available and used. In fact, works such as [9] report similar best case performances with different datasets in Chinese.…”