Using Multi-level Features Construction for Discovering Key Twitterers

DOI

10.2991/ammee-17.2017.78How to use a DOI?

Keywords

Social Networks, key users, Networks Analysis, Information Diffusion.

Abstract

Identifying key users have become a focal problem in the area of online social networks. Tweets and Behaviors of people are two core facets for finding key users. Tweets of published by users spread support from different behaviors. However, existing literature on key users evaluation has mainly focused on methods based on one of them effects in social network, which make topic and behavior latent dimensions to difficult to interpret. How to modeling roles of user revealing the hidden relation based on tweets that users interested in and behaviors for dissemination of information in real social networks? In this paper, we tackle this problem by focusing on different behaviors of users and tweets similarity based on word embedding to measure the influence of users in social networks. We propose an algorithm using relation feature construction for key twitters extraction. Through extensive experiments comparing with different algorithms, we demonstrate that model is able to identify key users. Additional, the model that can be used to facilitate other tasks such as automated latent community discovery, and to track origin users

Copyright

© 2017, 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  - Jianjun Wu
PY  - 2017/06
DA  - 2017/06
TI  - Using Multi-level Features Construction for Discovering Key Twitterers
BT  - Proceedings of the Advances in Materials, Machinery, Electrical Engineering (AMMEE 2017)
PB  - Atlantis Press
SP  - 413
EP  - 421
SN  - 2352-5401
UR  - https://doi.org/10.2991/ammee-17.2017.78
DO  - 10.2991/ammee-17.2017.78
ID  - Wu2017/06
ER  -