Leveraging multidimensional features for policy opinion sentiment prediction

doi:10.1016/j.ins.2022.08.004

CASISD OpenIR > 系统分析与管理研究所

	Leveraging multidimensional features for policy opinion sentiment prediction
	Hou, Wenju ; Li, Ying ; Liu, Yijun1,2 ; Li, Qianqian1,2
发表期刊	INFORMATION SCIENCES
关键词	Policy opinion Sentiment prediction Deep learning Feature engineering
摘要	Previous online policy opinion analyses based on social media data have focused on topic detection and sentiment classification of policy opinion after a given period following pol-icy implementation. These approaches are limited and inefficient because they provide no opportunity to change citizens' opinions once they have been formed. Furthermore, incor-porating auxiliary information to enrich semantic representations is vital and challenging due to limited texts, and a lack of both semantic information and strict syntactic structure. Therefore, we propose a novel framework to extract and integrate multidimensional fea-tures from user-related and policy-related social media information and predict policy comment polarity in the policy release phase. First, we construct four machine learning models for model-induced features to capture topic-related and opinion-related features and identify the policy-opinion nexus. In addition, we integrate basic and behavioral user features. Then, we leverage multidimensional features to construct a stacked learning model for predicting the policy opinion. Finally, we conduct experiments on 20 policy com-ment datasets to demonstrate that our prediction framework can effectively predict public opinion about a policy once it is released. Our model provides key insights into policy opin-ions in advance and can enable policymakers to engage in better policy communication before opinion formation. (c) 2022 Elsevier Inc. All rights reserved.
	2022
卷号	610 页码:215
ISSN	0020-0255
文章类型	Article
DOI	10.1016/j.ins.2022.08.004
关键词[WOS]	SOCIAL MEDIA ; TWITTER ; NETWORK ; USERS
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000848341500014
引用统计
文献类型	期刊论文
条目标识符	http://ir.casisd.cn/handle/190111/12046
专题	系统分析与管理研究所
作者单位	1.Jilin Univ, Coll Comp Sci & Technol, Key Lab Symbol Computat & Knowledge Engn, Minist Educ, Changchun, Peoples R China 2.Chinese Acad Sci, Inst Sci & Dev, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Publ Policy & Management, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Hou, Wenju,Li, Ying,Liu, Yijun,et al. Leveraging multidimensional features for policy opinion sentiment prediction[J]. INFORMATION SCIENCES,2022,610:215.
APA	Hou, Wenju,Li, Ying,Liu, Yijun,&Li, Qianqian.(2022).Leveraging multidimensional features for policy opinion sentiment prediction.INFORMATION SCIENCES,610,215.
MLA	Hou, Wenju,et al."Leveraging multidimensional features for policy opinion sentiment prediction".INFORMATION SCIENCES 610(2022):215.