Construction of sentimental knowledge graph of Chinese government policy comments

Zhiyi Li, Yingluo Dai and Xiaolin Li

Knowledge Management Research & Practice, 2022, vol. 20, issue 1, 73-90

Abstract: Social Media Networks have developed into an important channel and platform for the collection and dissemination of policy information. Various policy comments on them have fully demonstrated the basic characteristics of big data. This paper introduces knowledge graphs into the sentiment analysis, analyses and sorts out the policy comments of China's mainstream social media platforms from 2016 to 2019, build a sentiment analysis dictionary, and then use the policy comments evaluation system to form sentiment knowledge graphs of policy comments that includes seven sentiments and five themes. The process of the sentiment knowledge graph constructed in this paper helps to more accurately understand the changes of online public opinion, and provides a theoretical basis for local governments to adjust the implementation of various policies. Apart from being the prototype of the automated sentiment knowledge graph system for policy comments, it can also be applied to other related hot topics.

Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/14778238.2021.1971056 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:tkmrxx:v:20:y:2022:i:1:p:73-90

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/tkmr20

DOI: 10.1080/14778238.2021.1971056

Access Statistics for this article

Knowledge Management Research & Practice is currently edited by Giovanni Schiuma

More articles in Knowledge Management Research & Practice from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().