A Convolutional Neural Network for Aspect-Level Sentiment Classification

Abstract

Sentiment analysis, including aspect-level sentiment classification, is an important basic natural language processing (NLP) task. Aspect-level sentiment can provide complete and in-depth results. Words with different contexts variably influence the aspect-level sentiment polarity of sentences, and polarity varies based on different aspects of a sentence. Recurrent neural networks (RNNs) are regarded as effective models for handling NLP and have performed well in aspect-level sentiment classification. Extensive literature exists on sentiment classification that utilizes convolutional neural networks (CNNs); however, no literature on aspect-level sentiment classification that uses CNNs is available. In the present study, we develop a CNN model for handling aspect-level sentiment classification. In our model, attention-based input layers are incorporated into CNN to introduce aspect information. In our experiment, in which a benchmark dataset from Twitter is compared with other models, incorporating aspect information into CNN improves aspect-level sentiment classification performance without using syntactic parser or other language features.

Recognition of Foodborne Pathogens Terahertz Spectrum Based on Convolutional Neural Network

“…Standard neural networks use a full-connection layer, the input matrix, vector, each neuron will act on all its elements, intensive connections, with the increase in the depth of neural networks, overfitting is more common. Convolutional neural networks [4] differ from ordinary neural networks in that the neurons used in convolutional neural networks are calculated in slightly different ways, and in mathematics convolution is slightly different, and it traverses the input matrix and vectors to achieve mapping relationships and calculate responses through the sliding window of convolutional nuclei. Compared with input characteristics, convolutional window size is often small, convolution is accompanied by down sampling problems, input propagation in the network will reduce the dimension layer by layer, filling and pooling of this non-computing unit will be combined with convolution neurons into a convolution module inserted into the network.…”

Building a Twitter Sentiment Analysis System with Recurrent Neural Networks

“…Xing et al [28] proposed a solution for twitter sentiment analysis which integrates both a CNN and an attention mechanism. Word embeddings are passed through an attentionbased input layer and then a CNN is used to analyze the sentiment that is expressed.…”

Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data

“…Conventionally, these inputs are the stemmed tweets. The CNN model has frequently been used to perform text classification [95]- [100], as well as sentiment analysis task [101]- [105].…”