Building a Domain Ontology for Online Rumors
Author Information
Author(s): Zhao Jianbo, Liu Huailiang, Zhang Weili, Sun Tong, Chen Qiuyi, Wang Yuehai, Cheng Jiale, Zhuang Yan, Zhang Xiaojin, Zhang Shanzhuang, Li Bowei, Ding Ruiyu
Primary Institution: Xidian University
Hypothesis
To effectively detect and govern online rumors, it is necessary to conduct in-depth semantic analysis and understand the content features of rumors.
Conclusion
The study successfully constructs a rumor domain ontology that can effectively analyze and reason different types of rumor texts.
Supporting Evidence
- The constructed ontology includes five parent classes and 88 subclasses.
- The ontology was verified using SWRL rules and a pellet reasoner.
- The study established a general rumor dataset containing 12,472 texts.
- An improved TFI network rumor domain ontology construction method was proposed.
- The ontology can effectively analyze complex, fuzzy, and uncertain information in online rumors.
Takeaway
This study created a system to help understand and manage online rumors by organizing their features into a structured format.
Methodology
The study used a combination of top-level ontology reuse, core document content feature extraction, and new concept discovery from real rumor datasets.
Potential Biases
The data sources are limited to mainstream rumor-refuting websites, which may not fully represent the diversity of online rumors.
Limitations
The ontology only considers content characteristics and does not account for user and communication characteristics, which may limit its effectiveness.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website