期刊
NEUROCOMPUTING
卷 464, 期 -, 页码 141-150出版社
ELSEVIER
DOI: 10.1016/j.neucom.2021.08.089
关键词
Microblog analysis; Sentiment classification; User historical preference
资金
- National Natural Science Foundation of China [61722211]
- Federal Ministry of Education and Research [01LE1806A]
- Beijing Academy of Artificial Intelligence [BAAI2019ZD0306]
- Technology Innovation and Application Development of Chongqing [cstc2020jscx-dxwtBX0014]
This study presents a novel neural microblog sentiment classification method that utilizes user’s contextual and historical state information to learn informative representations of microblog posts and alleviate the context sparsity problem. Experimental results demonstrate superior performance compared to state-of-the-art baselines in microblog sentiment analysis.
Microblog text is usually very short, thereby challenging existing sentiment classification methods by providing models with little context. Recently, historical user information has been widely used in many real-world applications, such as recommender systems. However, few research works consider user historical states in the loop of microblog sentiment analysis. In this work, we propose to involve historical user information for microblog sentiment analysis to alleviate the context sparsity problem. In particular, we propose a novel neural microblog sentiment classification method which learns informative representations of microblog posts by exploiting both a user's contextual information and his/her historical state information. The proposed method consists of four components, i.e., a micropost encoder, a user historical sentiment encoder, a User Historical Semantic Encoder, and a micropost sentiment classification component. Extensive experiments are conducted on real-world data collected from Weibo, and experimental results show that the proposed approach achieves superior performance as compared to state-of-the-art baselines. (C) 2021 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据