Neural Network based Approaches for Aspect-Based Sentiment Analysis

The research of Aspect-based Sentiment Analysis which is a process that has a more specific focus than general sentiment analysis is trending upwards in numbers. Stemming from Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs), novel approaches introduced new components like Graph Convolutional Networks (GCNs) and Transformers that improved the overall accuracy dramatically. Along with summarizing the models, the focus of this survey will be on comparing the several novel methods. Although this paper found that Dependency graph enhanced dual-transformer network (DGEDT) coupled with Bidirectional Encoder Representations from Transformers (BERT) is the best performing model thus far, this paper also identified challenges that needed to be addressed in order to better evaluate current and future models.