109 76

Detection of Rapidly Spreading Hashtags via Social Networks

Title
Detection of Rapidly Spreading Hashtags via Social Networks
Author
서지원
Keywords
Twitter; Tagging; Media; Inference algorithms; Probabilistic logic; Facebook; Social network; information diffusion; hashtag; probabilistic modeling; EM algorithm
Issue Date
2020-02
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Citation
IEEE ACCESS, v. 8, page. 39847-39860
Abstract
Social network services (SNSs) such as Twitter and Facebook have emerged as a new medium for communication. They offer a unique mechanism of sharing information by allowing users to receive all messages posted by those whom they ‘‘follow’’. As information in today’s SNSs often spreads in the form of hashtags, detecting rapidly spreading hashtags in SNSs has recently attracted much attention. In this paper, we propose realistic epidemic models to describe the probabilistic process of hashtag propagation. Our models take into account the way how users communicate in SNSs; moreover the models consider the influence of external media and separate it from internal diffusion within networks. Based on the proposed models, we develop efficient inference algorithms that measure the propagation rates of hashtags in social networks. With real-life social network data including hashtags and synthetic data obtained by simulating information diffusion, we show that the proposed algorithms find fast-spreading hashtags more accurately than existing algorithms. Moreover, our in-depth case study demonstrates that our algorithms correctly find internal diffusion rates of hashtags as well as external media influences.
URI
https://ieeexplore.ieee.org/document/9007679https://repository.hanyang.ac.kr/handle/20.500.11754/161288
ISSN
2169-3536
DOI
10.1109/ACCESS.2020.2976126
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
Detection of Rapidly Spreading Hashtags via Social Networks.pdfDownload
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE