计算机工程与应用2018，Vol.54Issue(13)：168-174,7.DOI:10.3778/j.issn.1002-8331.1701-0270
融合注意力机制和CNN-GRNN模型的读者情绪预测
Attention-based convolutional-gated recurrent neural network for reader’s emotion prediction
摘要
Abstract
The past reader’s emotion prediction methods are unable to capture the complex semantic and grammatical information in the document, and have mostly used in multi-label classification technology, which limit its development and application. To solve this problem, an improved method named attention-based convolutional-gated recurrent neural network for reader’s emotion prediction is presented. This method firstly divides the document into several sentences, and then adopts convolutional neural network to produce sentence-level representations from word vectors. Such useful sen-tence features can be sequentially integrated using gated recurrent neural network, and a novel attention mechanism is pro-posed to build a document-level representation according to their contribution to reader’s emotion prediction. Finally, a softmax regression is applied to predict reader’s emotion distributions. Experimental results on Yahoo news corpus demon-strate that the proposed method achieves better accuracy compared with state-of-the-art methods.关键词
情感分析/读者情绪预测/卷积神经网络/门限循环神经网络/注意力机制Key words
sentiment analysis/reader’s emotion prediction/convolutional neural network/gated recurrent neural net-work/attention mechanism分类
信息技术与安全科学引用本文复制引用
张琦,彭志平..融合注意力机制和CNN-GRNN模型的读者情绪预测[J].计算机工程与应用,2018,54(13):168-174,7.基金项目
国家自然科学基金(No.61272382,No.61672174) （No.61272382,No.61672174）
广东省科技计划项目(No.2015B020233019). （No.2015B020233019）
