Due to outstanding feature extraction ability, neural networks have recently achieved great success in sentiment analysis. However, one of the remaining challenges of sentiment analysis is to model long texts to consider the intrinsic relations between two sentences in the semantic meaning of a document. Moreover, most existing methods are not powerful enough to differentiate the importance of different document features. To address these problems, this paper proposes a new neural network model: AttBiLSTM-2DCNN, which entails two perspectives. First, a two-layer, bidirectional long short-term memory (BiLSTM) network is utilized to obtain the sentiment semantics of a document. The first BiLSTM layer learns the sentiment semantic representation from both directions of a sentence, and the second BiLSTM layer is used to encode the intrinsic relations of sentences into the document matrix representation with a feature dimension and a time-step dimension. Second, a two-dimensional convolutional neural network (2DCNN) is employed to obtain more sentiment dependencies between two sentences. Third, we utilize a two-layer attention mechanism to distinguish the importance of words and sentences in the document. Last, to validate the model, we perform an experiment on two public review datasets that are derived from Yelp2015 and IMDB. Accuracy, F1-Measure, and MSE are used as evaluation metrics. The experimental results show that our model can not only capture sentimental relations but also outperform certain state-of-the-art models.

Sentiment analysis (SA) is a vital research direction in natural language processing (NLP). Compared with the widely-concerned explicit sentiment analysis, implicit sentiment analysis (ISA) is more challenging and rarely studied due to the lack of sentiment words. However, existing implicit sentiment analysis methods are hard to identify implicit sentiment without the support of commonsense and contextual background. To address these limitations, we propose a knowledge-enhanced framework that integrates external knowledge graphs and contextual information for implicit sentiment analysis. We draw an analogy between the word in the target sentence and the knowledge graph entities and propose a retrieving and selecting method to automatically extract helpful knowledge graph entity embedding for implicit sentiment analysis. By introducing external knowledge from the knowledge graph, the proposed approach can extend semantic of implicit sentiment expressions. Then, a knowledge fusion module based on dynamic Coattention has been designed to integrate the extracted helpful knowledge with the context representation, effectively enriching the semantic representation of texts. The experiments on two implicit sentiment analysis datasets and two explicit sentiment analysis datasets prove that our model can achieve better performances in text sentiment analysis by fully utilizing external commonsense knowledge and context information.