Open Access

ARTICLE

Sentiment Classification Based on Piecewise Pooling Convolutional Neural Network

Yuhong Zhang^1,*, Qinqin Wang¹, Yuling Li¹, Xindong Wu²

1 School of Computer Science and Information Engineering, Hefei University of Technology, 485 Danxia Road, Shushan District, Hefei, 230009, China.
2 School of Computing and Informatics, University of Louisiana at Lafayette, 222 James R. Oliver Hall, Lafayette, Louisiana 70504, USA.

* Corresponding Author: Yuhong Zhang. Email: .

Computers, Materials & Continua 2018, 56(2), 285-297. https://doi.org/10.3970/cmc.2018.02604

Abstract

Recently, the effectiveness of neural networks, especially convolutional neural networks, has been validated in the field of natural language processing, in which, sentiment classification for online reviews is an important and challenging task. Existing convolutional neural networks extract important features of sentences without local features or the feature sequence. Thus, these models do not perform well, especially for transition sentences. To this end, we propose a Piecewise Pooling Convolutional Neural Network (PPCNN) for sentiment classification. Firstly, with a sentence presented by word vectors, convolution operation is introduced to obtain the convolution feature map vectors. Secondly, these vectors are segmented according to the positions of transition words in sentences. Thirdly, the most significant feature of each local segment is extracted using max pooling mechanism, and then the different aspects of features can be extracted. Specifically, the relative sequence of these features is preserved. Finally, after processed by the dropout algorithm, the softmax classifier is trained for sentiment classification. Experimental results show that the proposed method PPCNN is effective and superior to other baseline methods, especially for datasets with transition sentences.

---

Keywords

---