Abstract
Sentiment analysis is one of the significant application fields of natural language processing. Researchers divide the sentiment into explicit sentiment and implicit sentiment according to whether the expression contains sentiment words or not. Most of the existing research focuses on explicit sentiment tasks. However, implicit sentiment analysis is difficult to study because of its implicit tendency to express sentiment and the problem of “weak features” and “multi-confounding weak features”. We develop a novel model based on “Hierarchical Knowledge Enhancement and Multi-pooling”(HKEM), which fully integrates the knowledge information of different levels in the text through hierarchical knowledge enhancement to alleviate the “weak feature” problem. At the same time, the multi-pooling method is used to extract and analyze multiple features, and the “multi-confounding weak features” are modeled. In this paper, comparative experiments have been conducted on the SMP-ECISA2019 dataset, and the results show that the accuracy of this model is comparable to that of the current best model, and the F1 score is 5.9% higher than that of the best model, indicating that the model proposed in this paper can accurately analyze Chinese implicit sentiment and achieve the state-of-the-art in the comprehensive performance evaluation, which proves the effectiveness and superiority of the model in this paper.
Highlights
With the wide popularity of the Internet and the vigorous development of the social network, Internet users create, share, exchange views, opinions and emotions on the Internet [1], resulting in a variety of text data with human subjective emotion color, which has the characteristics of large quantity, wide range and strong real-time
In text representation vectors, we propose a novel representation learning idea based on hierarchical knowledge enhancement, which combines the feature information of character level, local unit and sentence level together, and represents the text as a vector in a new representation learning way, so that the representation vector can integrate rich and complete semantic information
In this paper, we introduce the idea of extracting multiple features into the implicit sentiment analysis of Chinese text, which can better model the situation that there are multiple implicit sentiment in the text
Summary
With the wide popularity of the Internet and the vigorous development of the social network, Internet users create, share, exchange views, opinions and emotions on the Internet [1], resulting in a variety of text data with human subjective emotion color, which has the characteristics of large quantity, wide range and strong real-time. Related work such as Wei et al [7] proposed a BiLSTM model with multipolarity orthogonal attention for implicit sentiment analysis, which has achieved better performance.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
