BROWSE
Detail
Conference Paper
Experimental Analysis Based on Binary Classification to Distinguish the Authenticity of Text with Social Network Data
Cited 1 time in 
Share 
Share
- Authors
- Seungwon Do, Junseong Bang
- Issue Date
- 2021-01
- Citation
- International Conference on Big Data and Smart Computing (BigComp) 2021, pp.283-286
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Social network platforms have made it possible to collect and store large amounts of text data. In the fields of defense, public safety, and security, social text data is used for data analysis research and network model learning. However, the authenticity of the text data causes distortion of the information or degrades the performance of the trained model. To solve this problem, we presented a binary classification model that distinguishes authenticity using a pre-trained language model and conducted an experiment using tweet data. As a result, we showed 81% accuracy and 0.61 Matthews correlation coefficient value.
- KSP Keywords
- Binary Classification, Classification models, Data analysis, Language model, Matthews correlation coefficient, Model learning, Network model, Public safety, Social network data, experimental analysis, social network(SN)