Enhancing implicit sentiment analysis via knowledge enhancement and context information

Abstract

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.