文献类型：期刊文献

英文题名：Stance Detection of Microblog Text Based on Two-Channel CNN-GRU Fusion Network

作者：Li, Wenfa[1];Xu, Yilong[2];Wang, Gongming[3]

通讯作者：Wang, GM[1]

机构：[1]Beijing Union Univ, Robot Coll, Beijing 100101, Peoples R China;[2]Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China;[3]Inspur Software Grp Co Ltd, Jinan 250000, Shandong, Peoples R China

第一机构：北京联合大学

通讯机构：[1]corresponding author), Inspur Software Grp Co Ltd, Jinan 250000, Shandong, Peoples R China.

年份：2019

卷号：7

起止页码：145944-145952

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20200608130980);Scopus(收录号：2-s2.0-85078952960);WOS:【SCI-EXPANDED(收录号:WOS:000498820700003)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61841601, in part by the Science and Technology Projects of Beijing Municipal Education Commission under Grant KM201711417011, and in part by the Premium Funding Project for Academic Human Resources Development in Beijing Union University under Grant BPHR2018EZ01.

语种：英文

外文关键词：Stance detection; natural language processing; deep learning; CNN; GRU

摘要：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.