Identification Of Seed Users Via Short Messages Based On Hadoop

DOI

10.2991/emcs-16.2016.370How to use a DOI?

Keywords

Seed user; Short message forwarding; Scoring policy; Hadoop; PageRank

Abstract

Short messages are an important part of social media network. Much work has been devoted to mining useful information and knowledge from short messages via classification and clustering approaches. However, in many situations, it is vital to identify some influential users whose messages will result in a large amount of forwarding, these users are called seed users. In this paper, directed graph has been setup to modelling short message forwarding, then, a "Reverse PageRank" scoring policy is presented to evaluate users. Finally, the Hadoop platform is introduced to facilitate processing of seed user identification. Experimental results show that the model and the scoring policy are effective in finding out seed users.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shicheng Gan
AU  - Pingjian Zhang
PY  - 2016/01
DA  - 2016/01
TI  - Identification Of Seed Users Via Short Messages Based On Hadoop
BT  - Proceedings of the 2016 International Conference on Education, Management, Computer and Society
PB  - Atlantis Press
SP  - 1477
EP  - 1480
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcs-16.2016.370
DO  - 10.2991/emcs-16.2016.370
ID  - Gan2016/01
ER  -