|
|
CLOpin: A Cross-lingual Knowledge Graph Framework for Public Opinion Analysis and Early Warning
|
Liang Ye,Li Xiaoyuan,Xu Hang,Hu Yiran
|
(School of Information Science and Technology, Beijing Foreign Studies University, Beijing 100089, China)
(School of Asian Studies, Beijing Foreign Studies University, Beijing 100089, China)
|
|
|
Abstract
[Objective] To explore the relation of information mapping among different languages, so as to achieve effective monitoring of public opinion outside the country and provide positive guidance to domestic audiences. [Method] A cross-linguistic knowledge mapping platform CLOpin is proposed in the field of public opinion analysis and early warning. The platform designs several toolsets for different scenarios to process cross-linguistic data sets, which can integrate data from various sources efficiently and construct a knowledge mapping to guide the implementation of cross-linguistic public opinion analysis and early warning. [Result] The results show that the information integrity of CLKG in one hour is 13.9% higher than single language knowledge graph, and only 5.2% lower than that of the latter in 24 hours. [Limitations] The construction of CLKG is constrained by the scarcity of domain experts, which has become the bottleneck of the construction of knowledge graph of non-common language. [Conclusion] In CLOpin platform, knowledge from different sources complements each other, which has a significant effect on expanding the amount of event information, and is conducive to accurately grasping the dynamics of public opinion and making early warning accordingly.
|
Published: 23 April 2020
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|