| Autor: |
Inafuku, Kazufumi, Fushimi, Takayasu, Satoh, Tetsuji |
| Zdroj: |
Social Network Analysis & Mining; 2/27/2022, Vol. 12 Issue 1, p1-14, 14p |
| Abstrakt: |
In social networking services (SNSs) such as Twitter and Facebook, a variety of information is transmitted among users, and the network grows through the chain of information transmission. The process of information diffusion can be regarded as a dynamic network with users as nodes and information transmission between users as edges. In this study, we propose a stimulation index that serves as an importance index of dynamic edges in information diffusion networks. The stimulation index quantifies the inducement degree of new information transmissions represented as subsequent edges in a dynamic network. Experiments confirm the validity of the index's stimulation score (STM) as a measure of importance in information diffusion through evaluation experiments using artificial data. In addition, the stimulation index accumulates data and thus enlarges as the network grows. In this work, we focus on the number of candidate nodes that can be directly or indirectly stimulated by an edge, and we propose k-DGC as a feature for edge occurrence. We predict the future stimulation index using k-DGC as input, and the results show consistent performance on a real Twitter dataset. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink