返回
Context-Specific Heterogeneous Graph Convolutional Network for Implicit Sentiment Analysis
DOI:10.1109/ACCESS.2020.2975244.png)
摘要
En 中文
Sentiment analysis has attracted considerable attention in recent years. In particular, implicit sentiment analysis is a more challenging problem due to the lack of sentiment words. It requires us to combine contextual information and precisely understand the emotion changing process. Graph convolutional network (GCN) techniques have been widely applied for sentiment analysis since they are capable of learning from complex structures and preserving global information. However, these models either only focus on extracting features from a single sentence and ignore the context semantic background or only consider the textual information and overlook the phrase dependency when constructing the graph. To address these problems, we propose a new context-specific heterogeneous graph convolutional network (CsHGCN) framework that can combine all context representations. It has a complete context that reflects the information on documents more comprehensively. It has a dependency structure that obtains token-token semantic acquisition more accurately. The experimental results on a Chinese implicit sentiment dataset show that our proposed model can effectively identify the target sentiment of sentences, and visualization of the attention layers further demonstrates that the model selects qualitatively informative tokens and sentences.
Keyword:
Sentiment analysis
Semantics
Task analysis
Data mining
Context modeling
Feature extraction
Convolutional neural networks
Implicit sentiment
sentiment analysis
heterogeneous graph
graph convolutional network (GCN)
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Enhancement of pyramid solar distiller performance using reflectors, cooling cycle, and dangled cords of wicks
Desalination
IF0
Identification of fact-implied implicit sentiment based on multi-level semantic fused representation

