Multi-Channel Convolutional Neural Network for Targeted Sentiment Classification

Abstract

In recent years, targeted sentiment analysis has received great attention as a fine-grained sentiment analysis. Determining the sentiment polarity of a specific target in a sentence is the main task. This paper proposes a multi-channel convolutional neural network (MCL-CNN) for targeted sentiment classification. Our approach can not only parallelize over the words of a sentence but also extract local features effectively. Contexts and targets can be more comprehensively utilized by using part-of-speech information, semantic information and interactive information so that diverse features can be obtained. Finally, experimental results on the SemEval 2014 dataset demonstrate the effectiveness of this method.